СПОСОБ И УСТРОЙСТВО АУТЕНТИФИКАЦИИ ЛИЧНОСТИ

Изобретение относится к вычислительной технике. Технический результат заключается в повышении эффективности и надежности аутентификации личности. Способ аутентификации личности, в котором получают собранный аудио- и видеопоток, когда аудио- и видеопоток формируется целевым объектом, который должен быть аутентифицирован; определяют, являются ли согласующимися чтение по губам и голос в аудио- и видеопотоке, и если чтение по губам и голос являются согласующимися, получают идентификатор объекта для целевого объекта путем использования голосового контента; определяют, содержит ли предварительно сохраненная регистрационная информация идентификатор объекта; получают физиологический признак модели, соответствующий идентификатору объекта, из регистрационной информации об объекте, если предварительно сохраненная регистрационная информация об объекте содержит идентификатор объекта; выполняют физиологическое распознавание по аудио- и видеопотоку, чтобы получать физиологический признак целевого объекта ...

Система и способ фильтрации запрошенной пользователем информации

Изобретение относится к средствам фильтрации запрошенной пользователем информации. Технический результат настоящего изобретения заключается в безопасном предоставлении пользователю запрошенной им информации за счет фильтрации упомянутой информации на основании анализа вероятности получения несанкционированного доступа к указанной информации. Собирают данные с мобильного устройства, где в качестве данных выступают, по меньшей мере, данные о характеристиках звука вокруг мобильного устройства, данные об иных мобильных устройствах, находящихся рядом с мобильным устройством, данные о геолокации мобильного устройства, данные о состоянии беспроводных сетей, в том числе о характеристиках сигнала беспроводных сетей. Формируют на основании собранных данных параметры модели окружающего пространства мобильного устройства, представляющей собой совокупность данных. Определяют с помощью модели окружающего пространства с использованием сформированных параметров степень информационной безопасности окружающего ...

Multi-user personalization at a voice interface device

Voice authentication system and method

METHOD, APPARATUS AND SYSTEM FOR SPEAKER VERIFICATION

Abstract The present disclosure relates to a method, apparatus, and system for speaker verification. The method includes: acquiring an audio recording; extracting speech signals from the audio recording; extracting features of the extracted speech signals; and determining whether the extracted speech signals represent speech by a predetermined speaker based on the extracted features and a speaker model trained with reference voice data of the predetermined speaker.

SECURE NONSCHEDULED VIDEO VISITATION SYSTEM

Described are methods and systems in which the censorship and supervision tasks normally performed by secured facility personnel are augmented or automated entirely by a Secure Nonscheduled Video Visitation System. In embodiments, the Secure Nonscheduled Video Visitation System performs voice biometrics, speech recognition, non-verbal audio classification, fingerprint and other biometric authentication, image object classification, facial recognition, body joint location determination analysis, and/or optical character recognition on the video visitation data. The Secure Nonscheduled Video Visitation utilizes these various analysis techniques in concert to determine if all rules and regulations enforced by the jurisdiction operation the secured facility are being followed by the parties to the video visitation session.

CORRELATING AUDIO SIGNALS FOR AUTHENTICATION

A computer system automatically authenticates a user to a server in response to determining that an audio signal received from one microphone positively correlates with an audio signal received from another microphone that is associated with a computing device at which the user is already authenticated to the server. Two audio signals are received from distinct microphones associated with first and second computing devices. A correlation module performs correlation on the two audio signals. An authentication module automatically authenticates a user to a server at the first computing device if it is determined that the first audio signal positively correlates with the second audio signal and the user is already authenticated to the server at the second computing device.

A sound source localization method and device

VOICE AND CONVERSATION RECOGNITION SYSTEM

A conversation recognition system on board a vehicle includes an acoustic sensor component that detects sound in a cabin of the vehicle, a voice recognition component coupled to the acoustic sensor component that analyzes the sound detected by the acoustic sensor component and identifies a plurality of utterances, and a conversation threading unit coupled to the voice recognition component that analyzes the utterances identified by the voice recognition component and identifies a plurality of conversations between a plurality of occupants of the vehicle. The conversation recognition system enables multiple conversations in an environment to be recognized and distinguished from each other.

METHODS AND VEHICLES FOR USING DETERMINED MOOD OF A HUMAN DRIVER AND MODERATING VEHICLE RESPONSE

Methods and systems for determining a mood of a human driver of a vehicle and using the mood for generating a vehicle response, is provided. One example method includes capturing, by a camera of the vehicle, a face of the human driver. The capturing is configured to capture a plurality of images over a period of time, and the plurality of images are analyzed to identify a facial expression and changes in the facial expression of the human driver over the period of time. The method further includes capturing, by a microphone of the vehicle, voice input of the human driver. The voice input is captured over the period of time. The voice input is analyzed to identify a voice profile and changes in the voice profile of the human driver over the period of time. The method processes, by a processor of the vehicle, a combination of the facial expression and the voice profile captured during the period of time to predict the mood of the human driver. The method generates the vehicle response that ...

VOICE CONTROL METHOD AND VOICE CONTROL SYSTEM

A voice control method and a voice control system are provided. The voice control method is adapted to a voice control apparatus connected to a local area network. The voice control method includes following steps. Voice data is received. A voice recognition is executed for the voice data to obtain voice print information and a prompt command corresponding to the voice data. Permission information corresponding to the voice print information is determined according to the voice print information and the prompt command. At least one electronic apparatus is controlled through the local area network according to at least one of the permission information, the prompt command and environment information.

Adaptation method for inter-person biometrics variability

Embodiments of a system and method for verifying an identity of a claimant are described. In accordance with one embodiment, a feature may be extracted from a biometric sample captured from a claimant claiming an identity. The extracted feature may be compared to a template associated with the identity to determine the similarity between the extracted feature and the template with the similarity between them being represented by a score. A determination may be made to determine whether the identity has a correction factor associated therewith. If the identity is determined to have a correction factor associated therewith, then the score may be modified using the correction factor. The score may then be compared to a threshold to determine whether to accept the claimant as the identity. In accordance with a further embodiment, during enrollment of a subject in a biometric verification system, a feature may be extracted from a biometric sample captured from the subject requesting enrollment ...

Voice activity detection method and device

Disclosed are a voice activity detection method and device, wherein the method includes: obtaining a combined VAD judgment result according to the number of continuous active frames, an average total SNR of all sub-bands, a tonal signal flag, and at least two existing VAD judgment results (107). The method and device are suitable for voice service, solve the problem of inaccurate VAD detection and realize highly accurate VAD judgment.

Method and device for analyzing data from a microphone

A method for analyzing data from a microphone, the microphone being arranged to continuously record audio data, the method comprising: continuously storing the recorded audio data in a buffer, receiving a first triggering signal at a first point in time, the first triggering signal pertaining to a request for analyzing the audio data presently being recorded by the microphone, transferring a predefined amount of recorded audio data stored prior to the first point in time and audio data stored after the first point in time to a conversation analyzing unit. The method is advantageous as the information that was momentarily available during a conversation in the form of sound waves is now analyzed and thus may be converted to a format compatible with information available from other sources of relevance to the user.

SPEAKER IDENTIFICATION

A method of speaker identification comprises receiving an audio signal representing speech; performing a first voice biometric process on the audio signal to attempt to identify whether the speech is the speech of an enrolled speaker; and, if the first voice biometric process makes an initial determination that the speech is the speech of an enrolled user, performing a second voice biometric process on the audio signal to attempt to identify whether the speech is the speech of the enrolled speaker. The second voice biometric process is selected to be more discriminative than the first voice biometric process.

Personalized gesture recognition for user interaction with assistant systems

In one embodiment, a method includes accessing a plurality of input tuples associated with a first user from a data store, wherein each input tuple comprises a gesture-input and a corresponding speech-input, determining a plurality of intents corresponding to the plurality of speech-inputs, respectively, by a natural-language understanding (NLU) module, generating a plurality of feature representations for the plurality of gesture-inputs based on one or more machine-learning models, determining a plurality of gesture identifiers for the plurality of gesture-inputs, respectively, based on their respective feature representations, associating the plurality of intents with the plurality of gesture identifiers, respectively, and training a personalized gesture-classification model for the first user based on the plurality of feature representations of their respective gesture-inputs and the associations between the plurality of intents and their respective gesture identifiers.

Facilitating automating home control

Systems, computer-implemented methods and/or computer program products that facilitate automating home control are provided. In one embodiment a computer-implemented method comprises: using a voice recognition component to identify user identification by analyzing voice signatures; using a face recognition component to determine user identification by analyzing facial features; using an authentication component to verify user identification and authorize control access to functionality of one or more automated home control systems; using a communication component to facilitate communication between the one or more automated home control systems and one or more devices; using a service component to execute a set of functions based on authorized user commands and information communicated from the one or more devices; and using a machine learning component to learn user preferences by correlating a set of functions with the authorized users commands.

VOICEPRINT-RECOGNITION-BASED SECURITY PROTECTION METHOD AND DEVICE

Provided is a voiceprint-recognition-based security protection method. The method includes: acquiring voice data of a current user of a terminal and extracting voiceprint characteristic information from the voice data; matching the extracted voiceprint characteristic information of the current user of the terminal with a pre-saved voiceprint model of an owner of the terminal, and judging whether the current user of the terminal is the owner of the terminal; and when judging that the current user of the terminal is not the owner of the terminal, performing security protection processing on the terminal.

HEADPHONE BIOMETRIC AUTHENTICATION

A voice signal in a headphone is detected. The voice signal includes a person speaking an audible command. Based on detecting the voice signal a first biometric signature of a user is retrieved. The first biometric signature is compared to one or more biometric features of the person. Based on comparing the first biometric signature to the one or more biometric features an authentication of the user is determined. An authentication action is performed based on the detected voice signal. The authentication action is performed in response to verifying the authentication.

METHOD AND DEVICE FOR SPEECH RECOGNITION

Embodiments of the present disclosure provide a method and device for speech recognition. The solution comprises: receiving a first speech signal issued by a user; performing analog to digital conversion on the first speech signal to generate a first digital signal after the analog to digital conversion; extracting a first speech parameter from the first digital signal, the first speech parameter describing a speech feature of the first speech signal; if the first speech parameter coincides with a first prestored speech parameter in a sample library, executing control signalling instructed by the first digital signal, the sample library prestoring prestored speech parameters of N users, N≧1. The solution can be applied in a speech recognition process and can improve the accuracy of speech recognition. 1. A method for speech recognition comprising:receiving a first speech signal issued by a user;performing analog to digital conversion on the first speech signal to generate a first digital signal after the analog to digital conversion;extracting a first speech parameter from the first digital signal, the first speech parameter describing a speech feature of the first speech signal;if the first speech parameter coincides with a first prestored speech parameter in a sample library, executing control signalling instructed by the first digital signal, the sample library prestoring prestored speech parameters of N users, N≧1.2. The method according to claim 1 , after extracting the first speech parameter from the first digital signal claim 1 , further comprising:if the first speech parameter does not coincide with any of the prestored speech parameters of the N users in the sample library, identifying the first speech signal as a stranger speech.3. The method according to claim 1 , wherein if the first speech parameter coincides with the first prestored speech parameter in the sample library claim 1 , executing control signalling instructed by the first digital signal ...

SYSTEM AND METHOD FOR AUTOMATED AGENT ASSISTANCE NEXT ACTIONS WITHIN A CLOUD-BASED CONTACT CENTER

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing.

Speaker verification method

A speaker verification method consist of the following steps: (1) generating a code book ( 42 ) covering a number of speakers having a number of training utterances for each of the speakers; (2) receiving a number of test utterances ( 44 ) from a speaker; (3) comparing ( 46 ) each of the test utterances to each of the training utterances for the speaker to form a number of decisions, one decision for each of the number of test utterances; (4) weighting each of the decisions ( 48 ) to form a number of weighted decisions; and (5) combining ( 50 ) the plurality of weighted decisions to form a verification decision ( 52 ).

Electronic device and method of performing function of electronic device

An electronic device and method are disclosed, including a communication circuit, a speaker, a microphone and a processor. The processor implements the method, including receiving a first voice input through the microphone, executing first voiceprint authentication on the first voice input including determining whether the first voice input matches voice information corresponding to a user stored in the electronic device, when the first voice input does not match the voice information, transmit a request message to at least one external electronic device for execution of a second voiceprint authentication, receive a response message indicating whether the first voice input is authenticated under the second voiceprint authentication, receive a second voice input through the microphone, and transmit second data related to the second voice input to an external server through the communication circuit for Automatic Speech Recognition (ASR) or Natural Language Understanding (NLU) on the second ...

Voiceprint recognition model construction

Technologies related to voiceprint recognition model construction are disclosed. In an implementation, a first voice input from a user is received. One or more predetermined keywords from the first voice input are detected. One or more voice segments corresponding to the one or more predetermined keywords are recorded. The voiceprint recognition model is trained based on the one or more voice segments. A second voice input is received from a user, and the user's identity is verified based on the second voice input using the voiceprint recognition model.

Unlocking Method and Electronic Device

An unlocking method and electronic device are provided. The unlocking method includes: receiving input sound information; and when a voiceprint feature of the sound information is within a preset voiceprint feature range of a corresponding function or application, unlocking the function or the application. The embodiments of the present disclosure enable a particular user group unable to operate a locked function or application, and enable other user groups to unlock a corresponding function or application in at least one unlocking manner, thereby more fully meeting a requirement of a user on encryption of a function or an application of a terminal.

SPEAKER RECOGNITION USING ADAPTIVE THRESHOLDING

Techniques related to speaker recognition are discussed. Such techniques may include determining an adaptive speaker recognition threshold based on a speech to noise ratio and noise type label corresponding to received audio and performing speaker recognition based on the adaptive speaker recognition threshold and a speaker recognition score corresponding to received audio.

Аdаptаtiоn mеthоd fоr intеr-pеrsоn biоmеtriсs vаriаbilitу

Еmbоdimеnts оf а sуstеm аnd mеthоd fоr vеrifуing аn idеntitу оf а сlаimаnt аrе dеsсribеd. In ассоrdаnсе with оnе еmbоdimеnt, а fеаturе mау bе ехtrасtеd frоm а biоmеtriс sаmplе саpturеd frоm а сlаimаnt сlаiming аn idеntitу. Тhе ехtrасtеd fеаturе mау bе соmpаrеd tо а tеmplаtе аssосiаtеd with thе idеntitу tо dеtеrminе thе similаritу bеtwееn thе ехtrасtеd fеаturе аnd thе tеmplаtе with thе similаritу bеtwееn thеm bеing rеprеsеntеd bу а sсоrе. А dеtеrminаtiоn mау bе mаdе tо dеtеrminе whеthеr thе idеntitу hаs а соrrесtiоn fасtоr аssосiаtеd thеrеwith. If thе idеntitу is dеtеrminеd tо hаvе а соrrесtiоn fасtоr аssосiаtеd thеrеwith, thеn thе sсоrе mау bе mоdifiеd using thе соrrесtiоn fасtоr. Тhе sсоrе mау thеn bе соmpаrеd tо а thrеshоld tо dеtеrminе whеthеr tо ассеpt thе сlаimаnt аs thе idеntitу. In ассоrdаnсе with а furthеr еmbоdimеnt, during еnrоllmеnt оf а subjесt in а biоmеtriс vеrifiсаtiоn sуstеm, а fеаturе mау bе ехtrасtеd frоm а biоmеtriс sаmplе саpturеd frоm thе subjесt rеquеsting еnrоllmеnt ...

DETERMINING RIDERSHIP ERRORS BY ANALYZING PROVIDER-REQUESTOR CONSISTENCY SIGNALS ACROSS RIDE STAGES

The present disclosure relates to systems, non-transitory computer readable media, and methods for detecting and providing a digital notification of whether a ridership error exists. For instance, a ridership error detection system identifies a transportation match between a requestor device and a provider device. The ridership error detection system determines one or more sets of provider-requestor consistency signals from the requestor device and the provider device across ride stages. For instance, the ridership error detection system analyzes location signals, IMU signals, audio signals, local wireless signals indicating distances between the requestor device and the provider device, and other signals to determine whether a ridership error exists. The ridership error detection system provides digital notifications to the provider device and the requestor device based on the ridership error determination.

System and method for automatic speech translation based on zero user interface

The Zero User Interface (UI)-based automatic speech translation system and method can solve problems such as the procedural inconvenience of inputting speech signals and the malfunction of speech recognition due to crosstalk when users who speak difference languages have a face-to-face conversation. The system includes an automatic speech translation server, speaker terminals and a counterpart terminal. The automatic speech translation server selects a speech signal of a speaker among multiple speech signals received from speaker terminals connected to an automatic speech translation service and transmits a result of translating the speech signal of the speaker into a target language to a counterpart terminal.

СПОСОБ ИДЕНТИФИКАЦИИ ГОВОРЯЩЕГО ПО ФОНОГРАММАМ ПРОИЗВОЛЬНОЙ УСТНОЙ РЕЧИ НА ОСНОВЕ ФОРМАНТНОГО ВЫРАВНИВАНИЯ

Изобретение относится к области опознавания говорящего по голосу, в частности к способам идентификации говорящего по фонограммам произвольной устной речи, предназначенным в том числе для криминалистических исследований. Сущность способа состоит в том, что идентификацию говорящего по фонограммам устной речи осуществляют путем оценки сходства между первой фонограммой говорящего и второй эталонной фонограммой. Для указанной оценки на первой и второй фонограммах выбирают опорные фрагменты речевых сигналов, на которых присутствуют формантные траектории, по крайней мере, трех формантных частот, сравнивают между собой опорные фрагменты, в которых совпадают значения, по крайней мере, двух формантных частот, оценивают сходство сравниваемых опорных фрагментов по совпадению значений остальных формантных частот, а сходство фонограмм в целом определяют по суммарной оценке сходства всех сравниваемых опорных фрагментов. Технический результат - обеспечивают надежную идентификацию говорящего как для длинных ...

Verfahren und Vorrichtung zur Messung der Ähnlichkeit von Sprachmusten

Speaker identification

A speaker recognition system extracts feature vectors from a signal to produce a match score to compare with stored models of enrolled speakers S1 S3, the method terminating upon speaker identification above a certainty threshold T1.2, or non-identification below a lower threshold T2.2. A Voice Activity Detector (VAD) triggers two parallel recognition processes S1 & S2 at t0 which accumulate match scores until respective high and low thresholds are reached at t1 and t2, at which point the process is disabled until S2 speaks at t4. The process may be re-enabled during this period by a speech start event, eg. a detected change of speaker direction or frequency. Only 1-2 seconds of resource-intensive biometric voice verification is thus required.

International Patent Application For Method, apparatus and system for speaker verification

The present disclosure relates to a method, apparatus, and system for speaker verification. The method includes: acquiring an audio recording;； extracting speech signals from the audio recording; extracting features of the extracted speech signals; and determining whether the extracted speech signals represent speech by a predetermined speaker based on the extracted features and a speaker model trained with reference voice data of the predetermined speaker.

Audio data transfer

Verification that data transmitted to a data processing module, such as voice biometric module 111, did originate from a microphone. A microphone authentication apparatus 204 maybe a trusted domain and have a first input for receiving analogue audio signals from a microphone transducer 201 and an analogue-to-digital converter 202 coupled to said first input for generating digital microphone data based on the received audio signals. A data authentication module 203 generates an authentication certificate (MAC) for certifying that the digital microphone data did pass via the authentication module. The authentication certificate is based on the digital microphone data and maybe an authentication module key. An output module outputs a digital microphone audio signal based on the digital microphone data with the authentication certificate. A biometric authentication module 111 may then verify that the received audio data was indeed generated by the microphone and not altered or generated by ...

Biometric processes

The present disclosure provides methods, systems, devices and computer program products for authenticating a user based on a comparison of audio signals to a stored voice model for an authorised user. In one aspect, a method comprises: obtaining a first audio signal that comprises a representation of a bone conducted signal, wherein the bone conducted signal is conducted via at least part of the user's skeleton; obtaining a second audio signal that comprises a representation of an air conducted signal; and, responsive to a determination that the first audio signal comprises a voice signal, enabling updates to the stored voice model for the authorised user based on the second audio signal.

Speaker identification

Speaker recognition

Detection of speech

IDENTIFICATION APPARATUS AND METHOD

Confidence levels for speaker recognition

Confidence levels for speaker recognition

The present invention relates to a system and method of making a verification decision within a speaker recognition system. A speech sample is gathered from a speaker over a period of time a verification score is then produce for said sample over the period. Once the verification score is determined a confidence measure is produced based on frame score observations from said sample over the period and a confidence measure calculated based on the standard Gaussian distribution. If the confidence measure indicates with a set level of confidence that the verification score is below the verification threshold the speaker is rejected and gathering process terminated.

Technologies for authenticating a speaker using voice biometrics

Technologies for authenticating a speaker in a voice authentication system using voice biometrics include a speech collection computing device and a speech authentication computing device. The speech collection computing device is configured to collect a speech signal from a speaker and transmit the speech signal to the speech authentication computing device. The speech authentication computing device is configured to compute a speech signal feature vector for the received speech signal, retrieve a speech signal classifier associated with the speaker, and feed the speech signal feature vector to the retrieved speech signal classifier. Additionally, the speech authentication computing device is configured to determine whether the speaker is an authorized speaker based on an output of the retrieved speech signal classifier. Additional embodiments are described herein.

COMPUTER PLATFORM AND METHOD FOR SECURELY EXCHANGING CONFIDENTIAL DATA AND GENERATING LEGAL DOCUMENTS

A system and method for securely exchanging confidential data and compiling legal documents, and performing particular legal actions using the confidential data, the documents being compiled based on features such as user location and verified user identity.

СПОСОБ ИДЕНТИФИКАЦИИ ГОВОРЯЩЕГО ПО ФОНОГРАММАМ ПРОИЗВОЛЬНОЙ УСТНОЙ РЕЧИ НА ОСНОВЕ ФОРМАНТНОГО ВЫРАВНИВАНИЯ

Способ идентификации говорящего по фонограммам произвольной устной речи на основе формантного выравнивания. Предлагаемый способ позволяет осуществлять надежную идентификацию говорящего как для длинных, так и для коротких фонограмм, фонограмм, записанных в различных каналах с высоким уровнем помех и искажений, а также фонограмм с произвольной устной речью дикторов, находящихся в различных психофизиологических состояниях, говорящих на различающихся языках, что обеспечивает широкую область применения предлагаемого способа, в том числе в криминалистических исследованиях. Идентификации говорящего по фонограммам устной речи осуществляют путем оценки сходства между первой фонограммой говорящего и второй эталонной фонограммой. Для указанной оценки на первой и второй фонограммах выбирают опорные фрагменты речевых сигналов, на которых присутствуют формантные траектории по крайней мере трех формант, сравнивают между собой опорные фрагменты, в которых совпадают значения по крайней мере двух формантных ...

СПОСОБ ИДЕНТИФИКАЦИИ ГОВОРЯЩЕГО ПО ФОНОГРАММАМ ПРОИЗВОЛЬНОЙ УСТНОЙ РЕЧИ НА ОСНОВЕ ФОРМАНТНОГО ВЫРАВНИВАНИЯ

Предлагаемый способ идентификации говорящего по фонограммам произвольной устной речи на основе формантного выравнивания позволяет осуществлять надежную идентификацию говорящего как для длинных, так и для коротких фонограмм, фонограмм, записанных в различных каналах с высоким уровнем помех и искажений, а также фонограмм с произвольной устной речью дикторов, находящихся в различных психофизиологических состояниях, говорящих на различающихся языках, что обеспечивает широкую область применения предлагаемого способа, в том числе в криминалистических исследованиях. Идентификация говорящего по фонограммам устной речи осуществляют путем оценки сходства между первой фонограммой говорящего и второй, эталонной фонограммой. Для указанной оценки на первой и второй фонограммах выбирают опорные фрагменты речевых сигналов, на которых присутствуют формантные траектории по крайней мере трех формант, сравнивают между собой опорные фрагменты, в которых совпадают значения по крайней мере двух формантных частот ...

SPEAKER VERIFICATION COMPUTER SYSTEM WITH TEXTUAL TRANSCRIPT ADAPTATIONS OF UNIVERSAL BACKGROUND MODEL AND ENROLLED SPEAKER MODEL

Voice recognition processing device, the voice recognition process and display device

성문 정보 관리 방법 및 장치, 및 신원 인증 방법 및 시스템

... 본 출원은 제1 사용자의 음성 정보를 얻기 위하여 연관된 시스템 내에 저장된 이력 음성 파일의 필터링, 텍스트 인식 처리에 의한 음성 정보에 대응하는 텍스트 정보 취득, 및 음성 정보 및 대응하는 텍스트 정보를 제1 사용자의 기준 성문 정보로 편집을 포함하는 성문 정보 관리 방법 및 장치, 및 신원 인증 방법 및 시스템에 관한 것이다. 기준 성문 정보 내의 텍스트 정보 및 음성 정보가 모두 연관된 시스템에 의해 사전 설정되지 않고 상술한 이력 음성 파일 기반으로 취득되므로, 즉, 공개되지 않으므로, 신원 인증이 실행될 때 다시 읽어져야 할 텍스트 정보의 특정한 내용을 사용자가 예견할 수 없고, 따라서 사전 녹음된 음성 파일을 재생하여 성공적인 인증의 목적을 달성할 수 없다. 그러므로, 신원 인증이 본 출원의 실시예에 의해 제공되는 성문 정보 관리 방법 기반으로 수행되고, 인증 결과가 더 정확하며, 잠재적인 보안 위험이 존재하지 않으며, 계정의 보안이 강화된다.

IDENTITY AUTHENTICATION METHOD AND APPARATUS

CHINESE VOICE EMOTION EXTRACTION AND MODELING METHOD COMBINING EMOTION POINTS

The present invention is a Chinese voice emotion extraction and modeling method combining emotion points. The Chinese voice emotion point extraction method is as follows: formulating emotion point database specifications including pronouncer specifications, sound recording script design specifications, audio file naming specifications, etc.; collecting emotion point data; and evaluating the pleasure degree, activation degree and dominance degree (PAD) of the emotion point, i.e. at least ten evaluators different from the speaker performing a PAD subjective listening evaluation experiment on the emotion point data. The Chinese voice emotion point modeling method includes: first selecting a voice characteristic according to the Fisher rate to train a sex identification support vector machine (SVM) model; then respectively establishing emotion point hidden Markov models (HMM) for men's voice and women's voice, and selecting the corresponding HMM to classify the emotion point according to the ...

IDENTIFICATION APPARATUS AND METHOD

An audible command can be utilized to both permit identification of the speaker and to permit subsequent actions that comprise a corresponding response to the audible command when the identity of the speaker correlates with that of a previously authorized individual (Figure 1). Such identification can be supplemented with other identification mechanisms. Hierarchical levels of permission can be utilized, with or without confidence level thresholds, to further protect the device against unauthorized access and/or manipulation.

VOICE AUTHENTICATION DEVICE, VOICE AUTHENTICATION SYSTEM, AND VOICE AUTHENTICATION METHOD

There is provided a voice authentication device capable of authenticating a communication partner of a communication terminal device by the received voice and preventing communication with a malicious person. In this device, when a user specification input unit (201) is key-operated to specify a communication partner, a user specification signal is outputted to a voice data sample storage unit (202). In a communication unit (205), a reception voice signal received from a mobile telephone device (100) is outputted to a voice correlation unit (203). In the voice data sample storage unit (202), corresponding voice sample data is read out according to the user specification signal inputted from the user specification input unit (201) and outputted as the sample signal to the voice correlation unit (203). In the voice correlation unit (203), the sample signal inputted from the voice data sample storage unit (202) is correlated with the reception voice signal inputted from the communication unit ...

Computer-based systems for administering patterned passphrases

This disclosure describes computer-based techniques for administering a spoken patterned passphrase. A passphrase processing unit running on an administrator computer generates passphrase data for a secure system using acoustic data and video data representing a spoken phrase by a speaker. This passphrase includes a pattern of words or speech segments that are audible and words or speech segments that are inaudible. During authentication, a passphrase administration unit on the administrator computer receives acoustic and visual data of a spoken phrase by a person attempting to access the secure system and evaluates whether the spoken phrase includes the pattern of audible and inaudible words or speech segments associated with the account. In this way, the techniques discussed herein may enable the administrator computer to administer spoken passphrases with an additional degree of protection than a system that is limited to using linguistic or biometric content in passwords or passphrases ...

Recognizing speech in the presence of additional audio

The technology described in this document can be embodied in a computer-implemented method that includes receiving, at a processing system, a first signal including an output of a speaker device and an additional audio signal. The method also includes determining, by the processing system, based at least in part on a model trained to identify the output of the speaker device, that the additional audio signal corresponds to an utterance of a user. The method further includes initiating a reduction in an audio output level of the speaker device based on determining that the additional audio signal corresponds to the utterance of the user.

Systems and methods for authentication program enrollment

Various embodiments of the technology described herein alleviate the need to specifically request enrollment information from a user to enroll the user in a voice biometric authentication program. For example, the system can receive a voice interaction from a user where the voice interaction includes a request or a command having one or more portions. After the user is authenticated using non-voice biometric authentication information, the system enrolls the user into a voice biometric authentication program for at least one portion of the request or the command. The system also enrolls the user into the voice biometric authentication program for other requests or commands that include one of the at least one portion of the request or the command and portions of one or more second requests or commands for which the user has been enrolled into the voice biometric authentication program.

Method and device for processing voiceprint authentication

The present disclosure provides a method and a device for processing voiceprint authentication. The method includes: extracting a first feature vector for each first speech segment of a training set by a gender-mixed voiceprint baseline system based on Deep Neural Network; training a gender classifier according to the first feature vector for each first speech segment and a pre-labeled first gender label of each first speech segment; training Deep Neural Network models for different genders respectively according to speech data of different genders of the training set; and training uniform background models, feature vector extracting models and linear probability discriminant analysis models for different genders respectively according to the Deep Neural Network models for different genders and the speech data of different genders of the training set. A voiceprint authentication processing model for gender distinguishing is built, thus improving the efficiency and accuracy of voiceprint ...

Methods and system for reducing false positive voice print matching

The methods, apparatus, and systems described herein are designed to reduce false positive voice print matching with fraudulent callers. A voice print of a call is created and compared to known voice prints to determine if it matches one or more of the known voice prints, and to transaction data associated with a database of voice prints. The methods include a pre-processing step to separate speech from non-speech, selecting a number of elements that affect the voice print the most, and/or generating a first score based on the number of selected audio elements matching audio elements of a voice print from the plurality of fraudulent speakers, determining if the first score exceeds a predetermined threshold score for the fraudulent speaker, and comparing the selected audio elements for the unknown caller, where the score exceeds the predetermined threshold score, to the voice prints associated with the customer account.

MODIFYING INPUT BASED ON DETERMINED CHARACTERISTICS

One embodiment provides a method, including: receiving, at a device, input; processing, using a processor, the input to identify at least one user command; identifying, using a processor, a characteristic related to the at least one user command; and performing an action based on the at least one command and the characteristic. Other aspects are described and claimed.

User identification with voiceprints on online social networks

In one embodiment, a method includes, by one or more computing devices of an online social network, receiving, from a client system of a first user of the online social network, a first audio input from an unknown user, identifying one or more candidate users, wherein each candidate user is a user of the online social network within a threshold degree of separation of a known user, calculating, for each candidate user, a probability score representing a probability that the unknown user is the candidate user, wherein the probability score is based on a comparison of the first audio input to a voiceprint of the candidate user stored by the online social network, wherein each voiceprint comprises audio data for auditory identification of the candidate user, and identifying one of the candidate users as being the unknown user based on the calculated probability scores of the candidate users.

Voice recognition device configured to start voice recognition in response to user instruction

A voice recognition device includes a memory and a processor. The processor is configured to store in the memory, digital voice data corresponding to a voice signal input from a voice input unit, recognize a spoken voice utterance from the voice data after a voice input start instruction is received, determine whether to correct the recognition result of the spoken voice utterance based on a time interval from a time when the voice input start instruction is received to a time when the voice signal is input via the voice input unit, and correct the recognition result of the voice utterance based on the time interval.

TEMPORAL-SPATIAL DIGITAL FINGERPRINTING

A series of images of a physical object are captured while the object is changing or moving, and each image processed to form a corresponding digital fingerprint, each individual digital fingerprint including spatial characterizations of points of interest in the corresponding image. Corresponding temporal data is added or linked to each digital fingerprint based on its capture time or position in the series, so that an ensemble of the individual digital fingerprints forms an integrated digital fingerprint of the moving object event that may be stored for use in later identifying that object. The temporal-spatial characteristics of a point of interest may have unlimited dimensions, including but not limited to 3- or 4-dimensional location data. An audio record captured concurrently with the series of images may be analyzed to form a digital fingerprint such as a voiceprint and linked to the integrated digital fingerprint based on the temporal dimension.

SPEECH RECOGNITION METHOD, ELECTRONIC DEVICE, AND COMPUTER STORAGE MEDIUM

A speech recognition method includes segmenting captured voice information to obtain a plurality of voice segments, and extracting voiceprint information of the voice segments; matching the voiceprint information of the voice segments with a first stored voiceprint information to determine a set of filtered voice segments having voiceprint information that successfully matches the first stored voiceprint information; combining the set of filtered voice segments to obtain combined voice information, and determining combined semantic information of the combined voice information; and using the combined semantic information as a speech recognition result when the combined semantic information satisfies a preset rule.

MANAGING AGENT ENGAGEMENT IN A MAN-MACHINE DIALOG

Agents engage and disengage with users intelligently. Users can tell agents to remain engaged without requiring a wakeword. Engaged states can support modal dialogs and barge-in. Users can cause disengagement explicitly. Disengagement can be conditional based on timeout, change of user, or environmental conditions. Engagement can be one-time or recurrent. Recurrent states can be attentive or locked. Locked states can be unconditional or conditional, including being reserved to support user continuity. User continuity can be tested by matching parameters or tracking user by many modalities including microphone arrays, cameras, and other sensors.

System and method for tracking persons of interest via voiceprint

Disclosed are systems, methods, and computer readable media for tracking a person of interest. The method embodiment comprises identifying a person of interest, capturing a voiceprint of the person of interest, comparing a received voiceprint of a caller with the voiceprint of the person of interest, and tracking the caller if the voiceprint of the caller is a substantial match to the voiceprint of the person of interest.

METHODS AND SYSTEM FOR DISTRIBUTING INFORMATION VIA MULTIPLE FORMS OF DELIVERY SERVICES

A content distribution facilitation system is described comprising configured servers and a network interface configured to interface with a plurality of terminals in a client server relationship and optionally with a cloud-based storage system. A request from a first source for content comprising content criteria is received, the content criteria comprising content subject matter. At least a portion of the content request content criteria is transmitted to a selected content contributor. If recorded content is received from the first content contributor, the first source is provided with access to the received recorded content. The recorded content may be transmitted via one or more networks to one or more destination devices. Optionally, a voice analysis and/or facial recognition engine are utilized to determine if the recorded content is from the first content contributor.

System And Method Of Writing Electronic Prescriptions In A Telemedicine System

A telemedicine system including a care coordination software platform allows for patient monitoring at home and connects patients to their medical teams via telemedicine using a HIPAA compliant video portal augmented by remote assisted physical examination, performance of diagnostic testing including labs and x-rays, and provision of appropriate treatment and prescriptions. Medical care is provided at the patient's location without the patient having to travel or spend time in waiting rooms, provides treatment based on objective physical examination data and any appropriate diagnostic testing, and provides validation of patient identity. Healthcare providers are made available via online video encounters to communicate with patients. Allied healthcare workers are dispatched to be in physical proximity to the patient to assist in physical examination, and provide diagnostic data. Providers order appropriate treatments and prescriptions based on examination findings and diagnostics. The telemedicine ...

Biometrics platform

Systems and methods for analyzing digital recordings of the human voice in order to find characteristics unique to an individual. A biometrics engine may use an analytics service in a contact center to supply audio streams based on configured rules and providers for biometric detection. The analytics service may provide call audio data and attributes to connected engines based on a provider-set of selection rules. The connected providers send call audio data and attributes through the analytics service. The engines are notified when a new call is available for processing and can then retrieve chunks of audio data and call attributes by polling an analytics service interface. A mathematical model of the human vocal tract in the call audio data is created and/or matched against existing models. The result is analogous to a fingerprint, i.e., a pattern unique to an individual to within some level of probability.

Call context metadata

A computer detects a connected voice or video call between participants and records a brief media sample. Speech recognition is utilized to determine when the call is connected as well as to transcribe the content of the audio portion of the media sample. The recorded media sample and transcribed content is associated with the connected voice or video call such that a user may reference it at a later point. The computer additionally suggests creating or editing contact information associated with the participants of the connected voice or video call based on the transcribed content.

Mobile Devices, Methods, and Computer Program Products for Enhancing Social Interactions With Relevant Social Networking Information

Devices, methods, and computer program products for facilitating enhanced social interactions using a mobile device are disclosed. A method for facilitating an enhanced social interaction using a mobile device includes receiving an audio input at the mobile device, determining a salient portion of the audio input, receiving relevant information associated with the salient portion, and presenting the relevant information via the mobile device.

Аdаptаtiоn mеthоd fоr intеr-pеrsоn biоmеtriсs vаriаbilitу

Еmbоdimеnts оf а sуstеm аnd mеthоd fоr vеrifуing аn idеntitу оf а сlаimаnt аrе dеsсribеd. In ассоrdаnсе with оnе еmbоdimеnt, а fеаturе mау bе ехtrасtеd frоm а biоmеtriс sаmplе саpturеd frоm а сlаimаnt сlаiming аn idеntitу. Тhе ехtrасtеd fеаturе mау bе соmpаrеd tо а tеmplаtе аssосiаtеd with thе idеntitу tо dеtеrminе thе similаritу bеtwееn thе ехtrасtеd fеаturе аnd thе tеmplаtе with thе similаritу bеtwееn thеm bеing rеprеsеntеd bу а sсоrе. А dеtеrminаtiоn mау bе mаdе tо dеtеrminе whеthеr thе idеntitу hаs а соrrесtiоn fасtоr аssосiаtеd thеrеwith. If thе idеntitу is dеtеrminеd tо hаvе а соrrесtiоn fасtоr аssосiаtеd thеrеwith, thеn thе sсоrе mау bе mоdifiеd using thе соrrесtiоn fасtоr. Тhе sсоrе mау thеn bе соmpаrеd tо а thrеshоld tо dеtеrminе whеthеr tо ассеpt thе сlаimаnt аs thе idеntitу. In ассоrdаnсе with а furthеr еmbоdimеnt, during еnrоllmеnt оf а subjесt in а biоmеtriс vеrifiсаtiоn sуstеm, а fеаturе mау bе ехtrасtеd frоm а biоmеtriс sаmplе саpturеd frоm thе subjесt rеquеsting еnrоllmеnt ...

Аdаptаtiоn mеthоd fоr intеr-pеrsоn biоmеtriсs vаriаbilitу

Еmbоdimеnts оf а sуstеm аnd mеthоd fоr vеrifуing аn idеntitу оf а сlаimаnt аrе dеsсribеd. In ассоrdаnсе with оnе еmbоdimеnt, а fеаturе mау bе ехtrасtеd frоm а biоmеtriс sаmplе саpturеd frоm а сlаimаnt сlаiming аn idеntitу. Тhе ехtrасtеd fеаturе mау bе соmpаrеd tо а tеmplаtе аssосiаtеd with thе idеntitу tо dеtеrminе thе similаritу bеtwееn thе ехtrасtеd fеаturе аnd thе tеmplаtе with thе similаritу bеtwееn thеm bеing rеprеsеntеd bу а sсоrе. А dеtеrminаtiоn mау bе mаdе tо dеtеrminе whеthеr thе idеntitу hаs а соrrесtiоn fасtоr аssосiаtеd thеrеwith. If thе idеntitу is dеtеrminеd tо hаvе а соrrесtiоn fасtоr аssосiаtеd thеrеwith, thеn thе sсоrе mау bе mоdifiеd using thе соrrесtiоn fасtоr. Тhе sсоrе mау thеn bе соmpаrеd tо а thrеshоld tо dеtеrminе whеthеr tо ассеpt thе сlаimаnt аs thе idеntitу. In ассоrdаnсе with а furthеr еmbоdimеnt, during еnrоllmеnt оf а subjесt in а biоmеtriс vеrifiсаtiоn sуstеm, а fеаturе mау bе ехtrасtеd frоm а biоmеtriс sаmplе саpturеd frоm thе subjесt rеquеsting еnrоllmеnt ...

Аdаptаtiоn mеthоd fоr intеr-pеrsоn biоmеtriсs vаriаbilitу

Еmbоdimеnts оf а sуstеm аnd mеthоd fоr vеrifуing аn idеntitу оf а сlаimаnt аrе dеsсribеd. In ассоrdаnсе with оnе еmbоdimеnt, а fеаturе mау bе ехtrасtеd frоm а biоmеtriс sаmplе саpturеd frоm а сlаimаnt сlаiming аn idеntitу. Тhе ехtrасtеd fеаturе mау bе соmpаrеd tо а tеmplаtе аssосiаtеd with thе idеntitу tо dеtеrminе thе similаritу bеtwееn thе ехtrасtеd fеаturе аnd thе tеmplаtе with thе similаritу bеtwееn thеm bеing rеprеsеntеd bу а sсоrе. А dеtеrminаtiоn mау bе mаdе tо dеtеrminе whеthеr thе idеntitу hаs а соrrесtiоn fасtоr аssосiаtеd thеrеwith. If thе idеntitу is dеtеrminеd tо hаvе а соrrесtiоn fасtоr аssосiаtеd thеrеwith, thеn thе sсоrе mау bе mоdifiеd using thе соrrесtiоn fасtоr. Тhе sсоrе mау thеn bе соmpаrеd tо а thrеshоld tо dеtеrminе whеthеr tо ассеpt thе сlаimаnt аs thе idеntitу. In ассоrdаnсе with а furthеr еmbоdimеnt, during еnrоllmеnt оf а subjесt in а biоmеtriс vеrifiсаtiоn sуstеm, а fеаturе mау bе ехtrасtеd frоm а biоmеtriс sаmplе саpturеd frоm thе subjесt rеquеsting еnrоllmеnt ...

ELECTRONIC DEVICE AND METHOD FOR PROVIDING MEMORY SERVICE BY ELECTRONIC DEVICE

According to an embodiment, an electronic device comprises a communication module, a memory, and a processor configured to, upon obtaining a first utterance related to a memory service, prepare to store first information for the memory service for the first utterance and store the first information including essential information, sensitivity information for the first information, and an authentication method for the first information, detected from the first utterance, in the memory, and obtain a second utterance for looking up information related to the memory service, upon identifying that the obtained second utterance is one for looking up the first information, complete authentication based on the authentication method, and provide the essential information by a providing method determined based on the sensitivity information. Various other embodiments may be provided.

Adapting Hotword Recognition Based On Personalized Negatives

A method for adapting hotword recognition includes receiving audio data characterizing a hotword event detected by a first stage hotword detector in streaming audio captured by a user device. The method also includes processing, using a second stage hotword detector, the audio data to determine whether a hotword is detected by the second stage hot word detector in a first segment of the audio data. When the hotword is not detected by the second stage hotword detector, the method includes, classifying the first segment of the audio data as containing a negative hotword that caused a false detection of the hotword event in the streaming audio by the first stage hotword detector. Based on the first segment of the audio data classified as containing the negative hotword, the method includes updating the first stage hotword detector to prevent triggering the hotword event in subsequent audio data that contains the negative hotword.

SYSTEMS AND METHODS FOR MULTI-MODAL USER DEVICE AUTHENTICATION

Systems and methods for multi-modal user device authentication are disclosed. An example electronic device includes a first sensor, a microphone, a first camera, and a confidence analyzer to authenticate a subject as the authorized user in response to a user presence detection analyzer detecting a presence of the subject and one or more of (a) an audio data analyzer detecting a voice of an authorized user or (b) an image data analyzer detecting a feature of the authorized user. The example electronic device includes a processor to cause the electronic device to move from a first power state to a second power state in response to the confidence analyzer authenticating the user as the authorized user. The electronic device is to consume a greater amount of power in the second power state than the first power state.

Interrupting receipt of sensitive information

Systems and methods for interrupting disclosure of sensitive information are described. Sensitive information data associated with a user is maintained. A primary device detects commencement of a voice input to a secondary device. As the voice input is detected by the primary device, the voice input is analyzed to determine the content of the voice input. The content is compared to the sensitive information data to determine whether the voice input contains sensitive information. When the primary device determines the voice input contains sensitive information, a speaker of the primary device is controlled to generate a noise canceling signal which interrupts receipt of further sensitive information by the secondary device.

Ambient cooperative intelligence system and method

A method, computer program product, and computing system for initiating a session within an ACI platform; receiving an authentication request from a requester; and authenticating that the requester has the authority to access the ACI platform.

IDENTIFICATION OF A LOCAL SPEAKER

VOICE AUTHENTICATION DEVICE, VOICE AUTHENTICATION SYSTEM, AND VOICE AUTHENTICATION METHOD

PROBLEM TO BE SOLVED: To prevent a user from having a telephone conversation with an ill-intentioned person beforehand by realizing the sure individual identification with the incoming voice of a call party between communication terminal devices each other. SOLUTION: When the call party is designated by the key-operation of a user designation input part 201, a user designation signal is outputted to a voice data sample preservation part 202. A received voice signal received from a portable telephone device 100 is outputted to a voice collation part 203 in a communication part 205. Corresponding voice sample data are read out in accordance with the user designation signal inputted from the user designation input part 201 and outputted as a sample signal to the voice collation part 203 in the voice data sample preservation part 202. The sample signal inputted from the voice data sample preservation part 202 is collated with the received voice signal inputted from the communication part 205 ...

СПОСОБ И УСТРОЙСТВО АУТЕНТИФИКАЦИИ ЛИЧНОСТИ

Speaker verification

A set of features is extracted from an input portion of speech provided by a speaker. A first scoring means 4 scores the set of features with a first stored model of mixture components derived from sets of features extracted from input portions of speech provided by a plurality of speakers. A second scoring means 12 scores the set of features with a second stored model of mixture components derived from sets of features extracted from input portions of speech provided by the speaker to be identified. The results are compared, 16, to determine whether the input portion of speech did originate from that particular speaker. The first scoring means 4 scores the set of features with only part of the first stored model most likely to provide a good match to the set of features provided.

Multi-user personalization at a voice interface device

Speaker identification

A method of speaker identification comprises receiving an audio signal representing speech; performing a first voice biometric process on the audio signal to attempt to identify whether the speech is the speech of an enrolled speaker; and, if the first voice biometric process makes an initial determination that the speech is the speech of an enrolled user, performing a second voice bio metric process on the audio signal to attempt to identify whether the speech is the speech of the enrolled speaker. The second voice biometric process is selected to be more discriminative than the first voice biometric process.

Multi-user personalization at a voice interface device

Voice activated devices (190-1-N, fig. 1) receive freeform voice input from a user (eg. 102-1) and compare this to a set of trained voice models (550) in order to determine a first user. The voice input may include a hotword or wake word, to which the device may respond audibly (eg Good Morning Dave) before processing the request based on the users account. Users whose voices do not match a model may encounter restricted functionality. A particular device may be selected as a priority leader for performing the processing, and noise-reduction may also be performed.

Audio privacy based on user identification

Audio data transfer

Methods and apparatus for biometric authentication in an electronic device

Analysing speech signals

Speaker identification

A method of speaker identification comprises receiving an audio signal representing speech; determining whether it has properties indicating that it may be the result of a replay attack, performing a first voice biometric process on the audio signal to attempt to identify whether the speech is the speech of an enrolled speaker; and, if the first voice biometric process makes an initial determination that the speech is the speech of an enrolled user, performing a second voice biometric process on the audio signal to attempt to identify whether the speech is the speech of the enrolled speaker. The second voice biometric process is selected to be more discriminative than the first voice biometric process.

Secure nonscheduled video visitation system

Described are methods and systems in which the censorship and supervision tasks normally performed by secured facility personnel are augmented or automated entirely by a Secure Nonscheduled Video Visitation System. In embodiments, the Secure Nonscheduled Video Visitation System performs voice biometrics, speech recognition, non-verbal audio classification, fingerprint and other biometric authentication, image object classification, facial recognition, body joint location determination analysis, and/or optical character recognition on the video visitation data. The Secure Nonscheduled Video Visitation utilizes these various analysis techniques in concert to determine if all rules and regulations enforced by the jurisdiction operation the secured facility are being followed by the parties to the video visitation session.

Handsfree beam pattern configuration

An audio system that adjusts one or more beam patterns emitted by one or more loudspeaker arrays based on the preferences of users/listeners is described. The audio system includes an audio receiver that contains a listener location estimator, a listener identifier, and a voice command processor. Inputs from the listener location estimator, the listener identifier, and the voice command processor are fed into an array processor. The array processor drives the one or more loudspeaker arrays to emit beam patterns into the listening area based on inputs from each of these devices. By examining the location, preferred usage settings, and voice commands from listeners, the generated beam patterns are customized to the explicit and implicit preferences of the listeners with minimal direct input. Other embodiments are also described.

Identity authentication method and apparatus

Provided in the present application are an identity authentication method and apparatus, the method comprising: acquiring a collected audio-video stream produced by a target subject to be authenticated and determining whether the lip movement and speech in the audio-video stream are consistent, and if not consistent, then implementing speech recognition of the audio stream in the audio-video stream to obtain speech content to serve as a subject identifier of the target subject; if pre-stored subject registration information comprises the subject identifier, then acquire template physiological characteristics corresponding to the subject identifier from the subject registration information; implementing physiological identification of the video stream to obtain physiological characteristics of the target subject; comparing the physiological characteristics of the target subject with the template physiological characteristics to obtain comparison results, and if the comparison results satisfy ...

SYSTEM AND METHOD FOR VOICE AUTHENTICATION

A system and a method for single sign-on voice authentication that provides access to multiple voice recognition and artificial intelligence platforms, to multiple devices and to multiple third party web service systems.

FRAUDULENT REQUEST IDENTIFICATION FROM BEHAVIORAL DATA

Various examples described herein are directed to systems, methods, and computer-readable medium for routing distribution requests. A request for distribution of funds is received. The funds are in an account of a user. An activity window is determined. Data from within the activity window is collected. A risk score is calculated based on the data. The request is routed to a further verification queue based on the risk score. Additional information needed to verify the request is determined. The additional information is requested and received. The additional information is verified. Approval of the request is determined based on the verification of the additional information.

PATTERN RECOGNITION USING MULTIPLE REFERENCE MODELS

A method and apparatus for pattern recognition comprising comparing an input signal representing an unknown pattern with reference data representing each of a plurality of pre-defined patterns, at least one of the pre-defined patterns being represented by at least two instances of reference data. Successive segments of the input signal are compared with successive segments of the reference data and comparison results for each successive segment are generated. For each pre-defined pattern having at least two instances of reference data, the comparison results for the closest matching segment of reference data for each segment of the input signal are recorded to produce a composite comparison result for the said pre-defined pattern. The unknown pattern is the identified on the basis of the comparison results. Thus the effect of a mismatch between the input signal and each instance of the reference data is reduced by selecting the best segments from the instances of reference data for each ...

Method and apparatus for performing speaker recognition

PRONUNCIATION ASSESSMENT METHOD AND PRONUNCIATION ASSESSMENT SYSTEM USING SAME

Disclosed is a pronunciation assessment system which generates an assessment model for each word by extracting a feature vector for each word of native speaker′s pronunciation extracted from a native speaker′s voice database if a native speaker′s reference utterance signal does not exist, extracts a feature vector for each word for a utterance voice of a leaner, and performs a pronunciation assessment for each word by determining similarity between the feature vector for each word for the utterance voice of the leaner and the assessment model for each word. According to the present invention, the pronunciation assessment can be performed even if there is not information on a native speaker′s reference pronunciation. COPYRIGHT KIPO 2018 (100) Work pronunciation assessment feature extraction unit (210) Native speaker voice signal forced alignment unit (220) Native speaker transfer file DB (230) Native speaker voice signal DB (310) Learner voice signal voice recognition unit (410) Word assessment ...

핸즈프리 빔 패턴 구성

... 사용자/청취자의 선호도에 기초하여 하나 이상의 라우드스피커 어레이에 의해 방출된 하나 이상의 빔 패턴을 조정하기 위한 오디오 시스템이 기술된다. 오디오 시스템은 청취자 위치 추정부, 청취자 식별부, 및 보이스 커맨드 프로세서를 포함한 오디오 수신기를 포함한다. 청취자 위치 추정부, 청취자 식별부, 및 보이스 커맨드 프로세서에서의 입력들이 어레이 프로세서 내로 공급된다. 어레이 프로세서는 이들 디바이스들 각각에서의 입력들에 기초하여 하나 이상의 라우드스피커 어레이들을 구동시켜 청취 영역 내로 빔 패턴들을 방출하게 한다. 위치, 선호 사용 세팅 및 청취자로부터의 보이스 커맨드를 분석함으로써, 생성된 빔 패턴이 최소의 직접적 입력을 이용하여 사용자의 명시적 및 암시적 선호도에 따라 맞춤화된다. 다른 실시예들이 또한 기술된다.

Systems, methods, and media for generating hierarchical fused risk scores

Systems, methods, and media for generating fused risk scores for determining fraud in call data are provided herein. Some exemplary methods include generating a fused risk score used to determine fraud from call data by generating a fused risk score for a leg of call data, via a fuser module of an analysis system, the fused risk score being generated by fusing together two or more uniquely calculated fraud risk scores, each of the uniquely calculated fraud risk scores being generated by a sub-module of the analysis system; and storing the fused risk score in a storage device that is communicatively couplable with the fuser module.

DIALOG-BASED VOICEPRINT SECURITY FOR BUSINESS TRANSACTIONS

A system for biometrically securing business transactions uses speech recognition and voiceprint authentication to biometrically secure a transaction from a variety of client devices in a variety of media. A voiceprint authentication server receives a request from a third party requestor to authenticate a previously enrolled end user of a client device. A signature collection applet presents the user a randomly generated signature string, prompting the user to speak the string, and recording the user's as he speaks. After transmittal to the authentication server, the signature string is recognized using voice recognition software, and compared with a stored voiceprint, using voiceprint authentication software. An authentication result is reported to both user and requestor. Voiceprints are stored in a repository along with the associated user data. Enrollment is by way of a separate enrollment applet, wherein the end user provides user information and records a voiceprint, which is subsequently stored. 1. A system for securing a transaction , comprising:an authentication server, wherein said server receives a request from a requestor over a network to authenticate an enrolled user of a client device, based on said user's voiceprint; anda dialog-based signature collection component adapted to present said user a random signature string and record said signature string as the user speaks it, a recognizer adapted to recognize the recorded signature string; and', 'a voiceprint authenticator adapted to compare said recorded signature string with a stored voiceprint of said user;, 'said authentication server comprisingwherein said user is authenticated or rejected based on result of said comparison.2. The system of claim 1 , wherein said requestor comprises a server running a business application.3. The system of claim 1 , wherein said requestor comprises a telephony server.4. The system of claim 1 , wherein said requestor communicates with said server over either a data ...

VOICE PRINT IDENTIFICATION FOR IDENTIFYING SPEAKERS

Voice print identification for identifying speakers is provided. A plurality of speakers are recorded and associated with identity indicators. Voice prints for each speaker are associated with the plurality of recorded speakers. If the voice print for at least one speaker corresponds to a known user according to the identity indicators, a database entry associating the user with the voice print may be created. Additional information associated with the user may also be displayed. 1. A method for providing voice print identification , comprising:recording a plurality of speakers at an event;creating a plurality of voice prints, each voice print being associated with a speaker from the plurality of speakers;identifying at least one identity indicator for each of the plurality of speakers;identifying the event associated with recording the plurality of speakers;identifying a list of attendees for the event associated with the recording the plurality of speakers;correlating the at least one identity indicator, event, and the list of attendees to determine whether at least one of the plurality of voice prints corresponds to a particular speaker.2. The method of claim 1 , wherein the at least one identity indicator comprises at least one of the following: a location of the recording claim 1 , a time of the recording claim 1 , a caller ID claim 1 , a device identifier claim 1 , a host user claim 1 , a calendar entry associated with the event claim 1 , a recorded image claim 1 , and a voice to text segment.3. The method of claim 1 , further comprising:in response whether at least one of the plurality of voice prints corresponds to a particular speaker, displaying at least one information element associated with the particular speaker.4. The method of claim 3 , wherein the at least one information element comprises at least one of the following: a list of previous meetings with the particular speaker claim 3 , contact information associated with the particular speaker claim ...

System and method for automated agent assistance within a cloud-based contact center

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing.

System and method for automated scheduling using agent assist within a cloud-based contact center

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing.

System and method for speech-enabled automated agent assistance within a cloud-based contact center

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing.

SYSTEM AND METHOD FOR QUERYING MULTIPLE INFORMATION SOURCES USING AGENT ASSIST WITHIN A CLOUD-BASED CONTACT CENTER

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing. 1. A method , comprising:executing an automation infrastructure within a cloud-based contact center that includes a communication manager, speech-to-text converter, a natural language processor, and an inference processor exposed by application programming interfaces; andexecuting an agent assist functionality within the automation infrastructure that performs operations comprising:receiving a communication from a customer;presenting text associated with the communication in a unified user interface;automatically analyzing the communication to determine a subject of the customer's communication;automatically querying an in a plurality of information sources in real time formation source for at least one response to the subject; andpresenting the at least one response from the plurality of information sources the unified user interface.2. The method of claim 1 , further comprising:parsing the communication for key terms; andautomatically highlighting the key terms in the unified user interface.3. The method of claim 2 , the analyzing further comprising:inferring an intent of the customer using an intent inference module; anddetermining the keywords in accordance with the intent.4. The method of claim 1 , further comprising scrolling the unified user interface to receive subsequent communication from the customer and to present subsequent responses from the information source.5. The method of claim 1 , further comprising ranking a plurality of responses from the plurality of information sources in accordance with a relevance of each of ...

AUTOMATIC PAYMENT DETERMINATION

A computer system monitors one or more communication applications on a device of a user. The computer system identifies a communication that corresponds to a payment from a plurality of communications on the one or more communication applications. In response to the identifying the communication that corresponds to the payment, the computer system automatically identifying one or more other users associated with the payment without prompting the user for information. 1. A system , comprising:one or more computer-readable memories storing program instructions; and monitoring one or more communication applications on a device of a user;', 'identifying a communication that corresponds to a payment from a plurality of communications on the one or more communication applications; and', 'in response to the identifying the communication that corresponds to the payment, automatically identifying one or more other users associated with the payment without prompting the user for information., 'one or more processors configured to execute the program instructions to cause the system to perform operations comprising2. The system of claim 1 , wherein the automatically identifying the one or more other users associated with the payment comprises analyzing location information to determine that the one or more other users are within a threshold distance of the user.3. The system of claim 2 , wherein the automatically identifying the one or more other users associated with the payment further comprises referencing a social media account of the user to determine that the one or more other users are associated with the social media account of the user.4. The system of claim 1 , wherein the automatically identifying the one or more other users associated with the payment comprises utilizing natural language processing techniques to analyze the communication corresponding to the payment.5. The system of claim 1 , further comprising:in response to the identifying the one or more other ...

SPEAKER IDENTIFICATION ASSISTED BY CATEGORICAL CUES

Methods, computer program products, and systems are presented. The methods include, for instance: obtaining a media file including a speech by one or more speaker. The language of the speech is identified and biographic data of a speaker of the speech is generated by analyzing semantics and vocal characteristics of the speech. The speaker is diarized and confidence in a resulting speaker label is evaluated against a threshold. The speaker label is adjusted with the language of the speech and biographic data of the speaker and produced as speaker metadata of the media file. 1. A computer implemented method comprising:obtaining a media file having speech by one or more speaker;identifying a language of the speech by analyzing semantics of the language;generating speaker biographic data in preconfigured categories, wherein the generating includes analyzing frequently used words of the speech;diarizing the media file by adjusting boundaries of segments of the media file and identifying respective speaker for respective segments;evaluating a confidence associated with a speaker as identified from the diarizing;adjusting a speaker label corresponding to the speaker to include the speaker, the language, and the speaker biographic data, responsive to the evaluating; andproducing the speaker label resulting from the adjusting as speaker metadata for a segment corresponding to the speaker.2. The computer implemented method of claim 1 , the evaluating further comprising: increasing the confidence responsive to ascertaining an evidence supporting that the speaker identified from the diarizing matches the speaker biographic data from the generating claim 1 , wherein the preconfigured categories are preconfigured demographic categories independent of the language of the speech.3. The computer implemented method of claim 1 , the evaluating further comprising: increasing the confidence responsive to ascertaining an evidence supporting that the speaker identified from the diarizing ...

METHODS AND SYSTEM FOR DISTRIBUTING INFORMATION VIA MULTIPLE FORMS OF DELIVERY SERVICES

A content distribution facilitation system is described comprising configured servers and a network interface configured to interface with a plurality of terminals in a client server relationship and optionally with a cloud-based storage system. A request from a first source for content comprising content criteria is received, the content criteria comprising content subject matter. At least a portion of the content request content criteria is transmitted to a selected content contributor. If recorded content is received from the first content contributor, the first source is provided with access to the received recorded content. The recorded content may be transmitted via one or more networks to one or more destination devices. Optionally, a voice analysis and/or facial recognition engine are utilized to determine if the recorded content is from the first content contributor. 1. (canceled)2. A content management and distribution system , comprising:a computer system comprising one or more computing devices;a network interface; and enable a first entity to access a group identification user interface enabling members of a communications group to be defined and enabling an associated group identifier to be defined;', 'receive, using the network interface, from a user device associated with the first entity, via the group identification user interface, identification of members to be included in a first communications group, and an associated first communications group identifier;', 'provide for display on the first entity user device a user interface comprising a field that enables the first entity to specify a content request and an interface that enables the first entity to identify one or more social media platforms to which the requested content is to be shared;', 'provide for display on the first entity user device a user interface that enables the first entity to select the first communications group;', 'receive a selection of the first communications group by ...

AUTOMATIC PAYMENT DETERMINATION

A computer system monitors one or more communication applications on a device of a user. The computer system identifies a communication that corresponds to a payment from a plurality of communications on the one or more communication applications. In response to the identifying the communication that corresponds to the payment, the computer system automatically identifying one or more other users associated with the payment without prompting the user for information. 1. A system , comprising:one or more computer-readable memories storing program instructions; and monitoring one or more communication applications on a mobile device of a user;', 'identifying a communication that corresponds to a payment from a plurality of communications on the one or more communication applications;', 'in response to the identifying the communication that corresponds to the payment, automatically identifying one or more other users associated with the payment without prompting the user for information; and', 'in response to the automatically identifying the one or more others users associated with the payment, generating and providing, via the one or more communication applications, a user interface, the user interface including information corresponding to the identified one or more other users and a first selectable element, the first selectable element when selected via the provided user interface causes an approval of the payment., 'one or more processors configured to execute the program instructions to cause the system to perform operations comprising2. The system of claim 1 , wherein the automatically identifying the one or more other users associated with the payment comprises analyzing location information to determine that the one or more devices corresponding to the one or more other users are within a threshold distance of the mobile device of the user.3. The system of claim 1 , wherein the identifying the communication that corresponds to the payment includes analyzing ...

DETECTING SUBJECTS WITH DISORDERED BREATHING

There is provided an apparatus () for detecting subjects with disordered breathing. The apparatus () comprises one or more processors () configured to acquire an acoustic signal from an acoustic sensor () in an environment, determine a plurality of acoustic signal components from the acquired acoustic signal and determine a plurality of signal envelopes or energy signals based on the acoustic signal components. One or more processors () are also configured to analyze the determined plurality of signal envelopes or energy signals to detect whether there are one or more subjects in the environment with disordered breathing. 1. An apparatus for detecting subjects with disordered breathing , the apparatus comprising one or more processors configured to:acquire an acoustic signal from an acoustic sensor in an environment;determine a plurality of acoustic signal components from the acquired acoustic signal, the plurality of acoustic signal components differing from one another in respect of at least one signal characteristic or property;determine a plurality of signal envelopes or energy signals based on the acoustic signal components, at least one signal envelope being derived from each of the signal components; andanalyze the determined plurality of signal envelopes or energy signals to detect whether there are one or more subjects in the environment with disordered breathing, the analyzing comprising identifying repetition patterns in the determined plurality of signal envelopes or energy signals and a repetition interval for each of the identified repetition patterns.2. (canceled)3. An apparatus as claimed in claim 1 , wherein the plurality of acoustic signal components are for any one or more of:different frequency ranges;different Mel-frequency cepstral coefficients;different acoustic levels;different temporal characters; anddifferent spectral signatures.4. (canceled)5. An apparatus as claimed in claim 1 , wherein the one or more processors are configured to:compare ...

Selectively conditioning audio signals based on an audioprint of an object

A hearing aid system for selectively conditioning audio signals associated with a recognized object may include at least one processor. The processor may be programmed to receive audio signals acquired by a wearable microphone; analyze the received audio signals to obtain an isolated audio stream associated with a sound-emanating object in the environment of the user; determine an audioprint from the isolated audio stream; and use the audioprint to retrieve from a database information relating to the particular sound-emanating object. Based on the retrieved information, the processor may cause selective conditioning of at least one audio signal received by the wearable microphone from a region associated with the at least one sound-emanating object; and cause transmission of the at least one conditioned audio signal to a hearing interface device configured to provide sounds to an ear of the user. 1253-. (canceled)254. A hearing aid system for selectively conditioning audio signals associated with a recognized object , the hearing aid system comprising: receive audio signals acquired by a wearable microphone, wherein the audio signals are representative of sounds emanating from objects in an environment of a user;', 'analyze the received audio signals to obtain an isolated audio stream associated with a sound-emanating object in the environment of the user;', 'determine an audioprint from the isolated audio stream;', 'use the audioprint to retrieve from a database information relating to the particular sound-emanating object;', 'based on the retrieved information, cause selective conditioning of at least one audio signal received by the wearable microphone from a region associated with the at least one sound-emanating object; and', 'cause transmission of the at least one conditioned audio signal to a hearing interface device configured to provide sounds to an ear of the user., 'at least one processor programmed to255. The hearing aid system of claim 254 , wherein the ...

Virtual Waiting Rooms In A Telemedicine System

A telemedicine system including a care coordination software platform allows for patient monitoring at home and connects patients to their medical teams via telemedicine using a HIPAA compliant video portal augmented by remote assisted physical examination, performance of diagnostic testing including labs and x-rays, and provision of appropriate treatment and prescriptions. Medical care is provided at the patient's location without the patient having to travel or spend time in waiting rooms, provides treatment based on objective physical examination data and any appropriate diagnostic testing, and provides validation of patient identity. Healthcare providers are made available via online video encounters to communicate with patients. Allied healthcare workers are dispatched to be in physical proximity to the patient to assist in physical examination, and provide diagnostic data. Providers order appropriate treatments and prescriptions based on examination findings and diagnostics. The telemedicine system interfaces with medical sensors and collects data wired or wirelessly.

System And Method Of Patient Account Registration In A Telemedicine System

A telemedicine system including a care coordination software platform allows for patient monitoring at home and connects patients to their medical teams via telemedicine using a HIPAA compliant video portal augmented by remote assisted physical examination, performance of diagnostic testing including labs and x-rays, and provision of appropriate treatment and prescriptions. Medical care is provided at the patient's location without the patient having to travel or spend time in waiting rooms, provides treatment based on objective physical examination data and any appropriate diagnostic testing, and provides validation of patient identity. Healthcare providers are made available via online video encounters to communicate with patients. Allied healthcare workers are dispatched to be in physical proximity to the patient to assist in physical examination, and provide diagnostic data. Providers order appropriate treatments and prescriptions based on examination findings and diagnostics. The telemedicine system interfaces with medical sensors and collects data wired or wirelessly.

System And Method Of User Identity Validation in a Telemedicine System

A telemedicine system including a care coordination software platform allows for patient monitoring at home and connects patients to their medical teams via telemedicine using a HIPAA compliant video portal augmented by remote assisted physical examination, performance of diagnostic testing including labs and x-rays, and provision of appropriate treatment and prescriptions. Medical care is provided at the patient's location without the patient having to travel or spend time in waiting rooms, provides treatment based on objective physical examination data and any appropriate diagnostic testing, and provides validation of patient identity. Healthcare providers are made available via online video encounters to communicate with patients. Allied healthcare workers are dispatched to be in physical proximity to the patient to assist in physical examination, and provide diagnostic data. Providers order appropriate treatments and prescriptions based on examination findings and diagnostics. The telemedicine system interfaces with medical sensors and collects data wired or wirelessly. 1. A method of validating identity of a user , the method comprising:acquiring identity information on a computing device associated with the user;querying public and private record databases for identity information associated with the user;receiving a response to the query consisting of identity information associated with the user; andmaking a determination of validity of identity in accordance with the acquired identity information and public and private record database information received.2. The method according to claim 1 , wherein:the acquired identity information comprises at least one of facial recognition, voice recognition, fingerprint match, username and password, mobile device unique identification, cellular phone number and internet service provider identification; anddetermining validity of identity is made only if the at least one of said plurality of identity information is a ...

SMART AUDIO SYSTEM CAPABLE OF DETERMINING SPEAKER TYPE AND POSITION

There is provided a smart audio system including multiple audio devices and a central server. The central server confirms a model of every audio device and a position thereof in an operation area in a scan mode. The central server confirms a user position or a user state to accordingly control output power of a speaker of each of the multiple audio devices in an operation mode. 1. A smart audio system , comprising:multiple audio devices arranged at different positions in a room;an acoustic host, coupled to the multiple audio devices, and configured to sequentially control each of the multiple audio devices to generate predetermined sound;multiple microphones arranged in the room to receive the predetermined sound generated by the multiple audio devices to respectively generate audio data; anda central server coupled to the multiple microphones to determine a speaker type and a position of each of the multiple audio devices according to the audio data associated with the predetermined sound and generated by the multiple microphones.2. The smart audio system as claimed in claim 1 , wherein each of the multiple audio devices is arranged adjacent to one of the multiple microphones.3. The smart audio system as claimed in claim 1 , wherein the multiple microphones are directional microphones and respectively directed toward the multiple audio devices.4. The smart audio system as claimed in claim 1 , whereinthe acoustic host is configured to inform, by wireless data, the central server a current audio device that is controlled to generate the predetermined sound, andthe central server is configured to record the speaker type and the position corresponding to the current audio device according to the audio data.5. The smart audio system as claimed in claim 1 , wherein the speaker type comprises a frequency parameter of a speaker included in each of the multiple audio devices.6. The smart audio system as claimed in claim 1 , wherein after the central server recorded the ...

SYSTEM AND METHODS FOR PRONUNCIATION ANALYSIS-BASED SPEAKER VERIFICATION

A system and method for speaker verification based on using N-best speech recognition results. 1. A system for creating pronunciation analysis-based speaker verification comprising of:a speech recognition system that analyzes an utterance spoken by the user and returns a ranked list of recognized phrases;a speech analysis module that analyzes a list of recognized phrases and determines the parts of utterances that were pronounced correctly and the parts of utterances that were mispronounced;a star repository that contains star-like structures with the central node corresponding to a sequence of words or phonemes to be pronounced and the periphery nodes corresponding to results of ASR of pronunciation of the central node by a user or a group of users;a star generation system that finds sequences of phonemes, words and phrases that have homogeneous N-best results in multiple occurrences in one utterance and across multiple utterances for a user or a group of users and stores the results in star repository;a challenge phrase generation system that builds a set of phrases to be used to detect if a speaker is a legitimate user or an imposter using large corpora or internet at large to find phrases that correspond to stars that are consistently well recognized and stars that are consistently poorly recognized;a speaker verification system that uses challenge phrases to verify that the phrases that are consistently well recognized for a user continue to be well recognized during verification/authentication of a speaker, and the ones that were consistently mispronounced by a user are mispronounced during verification/authentication phase; anda human-machine interface that facilitates user registration and speaker verification phases.2. The system of where users' utterances are stored in an utterance repository accessible via the Internet.3. The system of claim 1 , further comprising a performance repository accessible via the Internet claim 1 , wherein users' ...

DETECTING REPLAY ATTACKS IN VOICE-BASED AUTHENTICATION

Disclosed are various embodiments for detecting replay attacks in voice-based authentication systems. In one embodiment, audio is captured via an audio input device. It is then verified that the audio includes a voice authentication factor spoken by a user. The audio is then compared with stored audio spoken by the user. If it is determined that an exact copy of the voice authentication factor is in the stored audio, one or more actions may be performed. 1. A method , comprising:receiving, via at least one of one or more computing devices, audio captured via an audio input device at a first geographic location;verifying, via at least one of the one or more computing devices, that the audio includes a voice authentication factor spoken by a user;receiving, via at least one of the one or more computing devices, information indicating that the user is physically present at a second geographic location instead of the first geographic location when the audio was captured; andperforming, via at least one of the one or more computing devices, at least one action in response to receiving the information, the at least one action comprising at least one of: causing a notification of authentication failure to be played by a speaker, requesting that the user provide another authentication factor, sending a notification to an administrator, blacklisting a network address, disabling access to an account associated with the user, storing the audio in a data store, or causing a honeypot mode to be entered by the one or more computing devices.2. The method of claim 1 , wherein the information includes a determination that the audio includes a voice in a language that differs from an expected language.3. The method of claim 1 , wherein the information includes a geolocation determination of the second geographic location.4. The method of claim 3 , wherein the second geographic location corresponds to a country never previously visited by the user.5. The method of claim 1 , further ...

Multi-User Personalization at a Voice Interface Device

A method at an electronic device with one or more microphones and a speaker includes receiving a first voice input; comparing the first voice input to one or more voice models; based on the comparing, determining whether the first voice input corresponds to any of a plurality of occupants, and according to the determination, authenticating an occupant and presenting a response, or restricting functionality of the electronic device. 1. A method , comprising: receiving a first voice input associated with a request for a service;', 'in response to receiving the first voice input, accessing one or more voice models each trained to a different one of the plurality of occupants;', 'comparing the first voice input to the one or more voice models;', 'based on the comparing, determining whether the first voice input corresponds to any of the plurality of occupants;', 'in accordance with a determination that the first voice input corresponds to a first occupant of the plurality of occupants, presenting at the electronic device a personalized response in accordance with a user account associated with the service; and', 'in accordance with a determination that the first voice input corresponds to none of the plurality of occupants: restricting functionality of the electronic device., 'at an electronic device with one or more microphones, a speaker, one or more processors, and memory storing one or more programs for execution by the one or more processors, the electronic device being located at a structure associated with a plurality of occupants and being configured to present information to the plurality of occupants2. The method of claim 1 , wherein the request is a request for a music service claim 1 , the personalized response is in accordance with a user account associated with a subscription to the music service claim 1 , and restricting functionality of the electronic device comprises presenting a generic response that does not involve a user account associated with a ...

AUDIO INPUT FILTERING BASED ON USER VERIFICATION

One embodiment provides a method, including: detecting, using an audio capture device associated with an information handling device, audible input; determining, using a processor, whether the audible input is associated with an authorized user; and performing, responsive to determining that the audible input is not associated with the authorized user, a silencing action associated with the audio capture device. Other aspects are described and claimed. 1. A method , comprising:detecting, using an audio capture device associated with an information handling device, audible input;determining, using a processor, whether the audible input is associated with an authorized user; andperforming, responsive to determining that the audible input is not associated with the authorized user, a silencing action associated with the audio capture device.2. The method of claim 1 , wherein the determining comprises:accessing a database comprising a voiceprint associated with the authorized user; anddetermining whether the audible input shares a predetermined level of similarity with the voiceprint.3. The method of claim 2 , further comprising training the voiceprint with voice input provided to a voice-based application.4. The method of claim 3 , wherein the training comprises:capturing at least one characteristic of the voice input; andupdating the voiceprint with the at least one characteristic.5. The method of claim 3 , further comprising:capturing, using an image capture device associated with the information handling device and during provision of the voice input, at least one image;ascertaining, using the at least one image, whether the voice input was provided by the authorized user; andupdating, responsive to ascertaining that the voice input was provided by the authorized user, the voiceprint.6. The method of claim 5 , wherein the ascertaining comprises identifying whether a visual aspect of the at least one image corresponds to an audio aspect of the voice input.7. The ...

SYSTEM AND METHOD FOR ASSISTING COMMUNICATION THROUGH PREDICTIVE SPEECH

A system and method for assisting communication through predictive speech is provided. A database includes commonly used words, phrases, and images, each associated with at least one context cue. A processor is configured to determine the user's context and display a number of possible initial words, phrases, or images associated with the determined context. A text field is updated with selected words, phrases, or images. The words, phrases, or literal equivalents of the images are audibly transmitted. 1. A system for assisting communication through predictive speech comprising:a user device comprising a display;a database comprising words, phrases, and images, wherein each of the words, phrases, and images are associated with one or more context cues; and determine user context;', 'display a number of possible initial phrases;', 'monitor for user input selecting one of the number of initial phrases;', 'display, at the user device, the selected initial phrase at a text field;', 'query the database for words, phrases, or images associated with a context cue matching the determined user context;', 'display the returned words, phrases, or images at a predictive field at the user device;', 'monitor for user input selecting one or more of the displayed words, phrases, or images;', 'update the displayed text field to input the selected words, phrases, or images; and', 'audibly transmitting the words, phrases, or literal equivalents of the images in the displayed text., 'an electronic storage device comprising software instructions, which when executed by a processor, configure the user device to2. The system of wherein:the context cues comprise other words, phrases, or images commonly used by the user such that words, phrases, or images selected more often by the user are displayed within the predictive field.3. The system of wherein:the context cues comprise one or more complete sentences such that the words, phrases, or images displayed at the predictive field form ...

REVERBERATION COMPENSATION FOR FAR-FIELD SPEAKER RECOGNITION

Techniques are provided for reverberation compensation for far-field speaker recognition. A methodology implementing the techniques according to an embodiment includes receiving an authentication audio signal associated with speech of a user and extracting features from the authentication audio signal. The method also includes scoring results of application of one or more speaker models to the extracted features. Each of the speaker models is trained based on a training audio signal processed by a reverberation simulator to simulate selected far-field environmental effects to be associated with that speaker model. The method further includes selecting one of the speaker models, based on the score, and mapping the selected speaker model to a known speaker identification or label that is associated with the user. 1. (canceled)2. At least one non-transitory computer readable medium comprising instructions that , when executed , cause at least one processor to at least:access a source utterance;artificially create reverberated speech based on a room dimension, a reflection coefficient, and the source utterance; andtrain a far-field machine learning model to recognize speech using the artificially created reverberated speech.3. The at least one non-transitory computer readable medium of claim 2 , wherein the source utterance is a near field utterance.4. The at least one non-transitory computer readable medium of claim 2 , wherein the instructions claim 2 , when executed claim 2 , cause the at least one processor to train the far-field machine learning model using gradient descent.5. The at least one non-transitory computer readable medium of claim 2 , wherein the instructions claim 2 , when executed claim 2 , cause the at least one processor to store the model in a machine readable storage.6. The at least one non-transitory computer readable medium of claim 2 , wherein the instructions claim 2 , when executed claim 2 , cause the at least one processor to:access spoken ...

DETECTING DEEP-FAKE AUDIO THROUGH VOCAL TRACT RECONSTRUCTION

A method is provided for identifying synthetic “deep-fake” audio samples versus organic audio samples. Methods may include: generating a model of a vocal tract using one or more organic audio samples from a user; identifying a set of bigram-feature pairs from the one or more audio samples; estimating the cross-sectional area of the vocal tract of the user when speaking the set of bigram-feature pairs; receiving a candidate audio sample; identifying bigram-feature pairs of the candidate audio sample that are in the set of bigram-feature pairs; calculating a cross-sectional area of a theoretical vocal tract of a user when speaking the identified bigram-feature pairs; and identifying the candidate audio sample as a deep-fake audio sample in response to the calculated cross-sectional area of the theoretical vocal tract of a user failing to correspond within a predetermined measure of the estimated cross sectional area of the vocal tract of the user. 1. An apparatus comprising at least one processor and at least one memory including computer program code , the at least one memory and computer program code configured to , with the processor , cause the apparatus to at least:generate a model of a vocal tract based at least in part on frequency response of one or more organic audio samples from a user;identify a set of bigram-feature pairs from the one or more organic audio samples;estimate, from the generated model of the vocal tract, the cross-sectional area of the vocal tract of the user when speaking the set of bigram-feature pairs;receive a candidate audio sample;identify bigram-feature pairs of the candidate audio sample that are in the set of bigram-feature pairs;calculate a cross-sectional area of a theoretical vocal tract of a user when speaking the identified bigram-feature pairs of the candidate audio sample; andidentify the candidate audio sample as a deep-fake audio sample in response to the calculated cross-sectional area of the theoretical vocal tract of a ...

ZERO-KNOWLEDGE MULTIPARTY SECURE SHARING OF VOICEPRINTS

Disclosed herein are embodiments of systems and methods for zero-knowledge multiparty secure sharing of voiceprints. In an embodiment, an illustrative computer may receive, through a remote server, a plurality of encrypted voiceprints. When the computer receives an incoming call, the computer may generate a plaintext i-vector of the incoming call. Using the plaintext i-vector and the encrypted voiceprints, the computer may generate one or more encrypted comparison models. The remote server may decrypt the encrypted comparison model to generate similarity scores between the plaintext i-vector and the plurality of encrypted voiceprints. 1. A computer implemented method comprising:receiving, by a computer from a first client computer, an encrypted voiceprint model and a random number, wherein the random number is encrypted using a public key of the computer;decrypting, by the computer, the random number using a private key of the computer;transmitting, by the computer, the encrypted voiceprint model to a second client computer;receiving, by the computer, one or more encrypted comparison models generated by the second client computer based upon comparing the encrypted voiceprint model and plaintext voiceprint;determining, by the computer, a similarity score between the encrypted voiceprint model and the plaintext voiceprint using the random number on the one or more encrypted comparison models; andtransmitting, by the computer, the similarity score to the second client computer to authenticate a speaker of a voice associated with the plaintext voiceprint or to identify a fraudulent caller.2. The method of claim 1 , wherein the encrypted voiceprint model is encrypted using properties from a Diffie-Hellman key exchange protocol.3. The method of claim 1 , wherein the encrypted voiceprint model is encrypted using properties from an elliptical curve cryptography key exchange protocol.4. The method of claim 1 , wherein determining the similarity score comprises:retrieving, by ...

DETECTING VOICE-BASED ATTACKS AGAINST SMART SPEAKERS

Techniques for operating a voice-activated computing device are provided. These techniques can be used to prevent voice-based attacks on such devices. An example method according to these techniques includes receiving audio content comprising a voice command, monitoring electromagnetic (EM) emissions using an EM detector of the voice-activated computing device, determining whether the audio content comprising the voice command was generated electronically or was issued by a human user based on the EM emissions detected while receiving the audio content comprising the voice command, and preventing the voice command from being executed by the voice-activated computing device responsive to determining that the voice command was generated electronically. 1. A method for operating a voice-activated computing device , the method comprising:receiving audio content comprising a voice command;monitoring electromagnetic (EM) emissions using an EM detector of the voice-activated computing device;determining whether the audio content comprising the voice command was generated electronically or was issued by a human user based on the EM emissions detected while receiving the audio content comprising the voice command; andpreventing the voice command from being executed by the voice-activated computing device responsive to determining that the voice command was generated electronically.2. The method of claim 1 , wherein determining whether the audio content comprising the voice command was issued electronically or by a human user further comprises:correlating changes in the audio content comprising the voice command with changes in the EM emissions detected by the EM detector to determine a security indicator; anddetermining whether the voice command was generated electronically based on the security indicator.3. The method of claim 2 , wherein the changes in the audio content comprise changes in at least one of the volume and the frequency of the audio content.4. The method of ...

PERSONALIZATION OF EXPERIENCES WITH DIGITAL ASSISTANTS IN COMMUNAL SETTINGS THROUGH VOICE AND QUERY PROCESSING

In non-limiting examples of the present disclosure, systems, methods and devices for providing personalized experiences to a computing device based on user input such as voice, text and gesture input are provided. Acoustic patterns associated with voice input, speech patterns, language patterns and natural language processing may be used to identify a specific user providing input from a plurality of users, identify user background characteristics and traits for the specific user, and topically categorize user input in a tiered hierarchical index. Topically categorized user input may be supplemented with user data and world knowledge and personalized responses and feedback for an identified specific user may be provided reactively and proactively. 120.-. (canceled)21. A computer-implemented method for personalized interaction with a digital assistant , comprising:receiving a first voice input from a first user;determining, based on an acoustical analysis of the first voice input, that a user profile exists for the first user, the user profile including user information from previous input of the first user;obtaining user characteristic information for the first user from the user profile;identifying one or more keywords from the first voice input;obtaining world knowledge for the first voice input based on the one or more keywords and the user characteristic information;providing a response to the first user based on the user characteristic information, the one or more keywords, and the world knowledge obtained for the first voice input;receiving a second voice input from a second user;determining based on an acoustical analysis of the second voice input that a user profile does not exist for the second user;identifying, from the second voice input, a background characteristic of the second user;identifying one or more keywords from the second voice input, wherein the one or more keywords are the same in the first and second voice inputs;obtaining world knowledge ...

Speech Recognition Method and Mobile Terminal

A speech recognition method and a mobile terminal relate to the field of electronic and information technologies, and can flexibly perform speech collection and improve a speech recognition rate. The method includes acquiring, by a mobile terminal, an orientation/motion status of the mobile terminal, and determining, according to the orientation/motion status, a voice collection apparatus for voice collection; acquiring, by the mobile terminal, a speech signal from the voice collection apparatus; and recognizing, by the mobile terminal, the speech signal. The present disclosure is applied to a scenario in which the mobile terminal performs speech recognition. 1. A speech recognition method , comprising:acquiring, by a mobile terminal, a distance to a user;determining, according to the distance to the user, a voice collection apparatus for voice collection, wherein the voice collection apparatus comprises a microphone array in the mobile terminal or a wearable voice collection apparatus;acquiring, by the mobile terminal, a speech signal from the voice collection apparatus, wherein the speech signal is obtained by converting voice collected by the voice collection apparatus; andrecognizing, by the mobile terminal, the speech signal.2. The method according to claim 1 , wherein determining the voice collection apparatus for voice collection comprises:determining whether the distance is less than a distance threshold, and if the distance is less than the distance threshold; anddetermining to use the microphone array as the voice collection apparatus,wherein acquiring the speech signal from the voice collection apparatus comprises acquiring, by the mobile terminal, the speech signal using the microphone array in the mobile terminal, andwherein the speech signal is obtained by converting voice collected by the microphone array.3. The method according to claim 1 , wherein determining the voice collection apparatus for voice collection comprises:determining whether the ...

SPEAKER SEPARATION BASED ON REAL-TIME LATENT SPEAKER STATE CHARACTERIZATION

Systems, methods, and non-transitory computer-readable media can obtain a stream of audio waveform data that represents speech involving a plurality of speakers. As the stream of audio waveform data is obtained, a plurality of audio chunks can be determined. An audio chunk can be associated with one or more identity embeddings. The stream of audio waveform data can be segmented into a plurality of segments based on the plurality of audio chunks and respective identity embeddings associated with the plurality of audio chunks. A segment can be associated with a speaker included in the plurality of speakers. Information describing the plurality of segments associated with the stream of audio waveform data can be provided. 1. A computer-implemented method comprising:obtaining, by a computing system, a stream of audio waveform data that represents speech involving a plurality of speakers;as the stream of audio waveform data is obtained, determining, by the computing system, a plurality of audio chunks, wherein an audio chunk is associated with one or more identity embeddings;segmenting, by the computing system, the stream of audio waveform data into a plurality of segments based on the plurality of audio chunks and respective identity embeddings associated with the plurality of audio chunks, wherein a segment can be associated with a speaker included in the plurality of speakers; andproviding, by the computing system, information describing the plurality of segments associated with the stream of audio waveform data.2. The computer-implemented method of claim 1 , wherein the segmenting is performed in real-time based on a computational graph.3. The computer-implemented method of claim 1 , wherein each audio chunk in the plurality of audio chunks corresponds to a fixed length of time.4. The computer-implemented method of claim 1 , wherein the one or more identity embeddings associated with the audio chunk are generated by a temporal convolutional network that pre-processes ...

Authentication method, authentication system, smart speaker and program

An authentication method includes a first step and a second step. The first step causes a voice including a predetermined character string to be output from a speaker 23 . The second step acquires voice information by receiving an utterance voice of the target user via a microphone 21 after the first step, and determines from the voice information whether the target user is the specific user or not. In the second step, it is determined whether a character string recognized from the voice information is matched to the predetermined character string. In the second step, it is determined whether characteristics of the utterance voice of the target user is matched to characteristics of the voice of the target user based on a characteristics amount recognized from the voice information and a characteristics amount of voice information registered in advance as the voice of the specific user.

ELECTRONIC DEVICE AND METHOD FOR VOICE RECOGNITION

A portable communication device is provided. A memory stores a first voice recognition module and a second voice recognition module. The first voice recognition module is capable of recognizing a wake-up voice command to activate the second voice recognition module. The second voice recognition module is capable of recognizing a plurality of voice commands other than the wake-up voice command. A processor is configured to recognize, using the first voice recognition module, the wake-up voice command from a first voice input, and activate the second voice recognition module. The processor is also configured to transmit, using the second voice recognition module, a second voice input to an external electronic device. The processor is further configured to recognize, using the second voice recognition module, a second voice command from a third voice input while a specified application is executed, and perform a specified function corresponding to the second voice command. 1. A portable communication device comprising:a display;communication circuitry;a microphone;a memory storing a first voice recognition module and a second voice recognition module, the first voice recognition module capable of recognizing a wake-up voice command to activate the second voice recognition module, and the second voice recognition module capable of recognizing a plurality of voice commands other than the wake-up voice command; and recognize, using the first voice recognition module, the wake-up voice command from a first voice input received via the microphone;', 'activate the second voice recognition module based at least in part on the recognizing of the wake-up voice command;', 'transmit, using the second voice recognition module, a second voice input received after the first voice input via the microphone to an external electronic device via the communication circuitry such that a first voice command of the plurality of voice commands is to be recognized by the external electronic ...

METHOD FOR PROVIDING TELEMATICS SERVICE USING VOICE RECOGNITION AND TELEMATICS SERVER USING THE SAME

A method for providing a telematics service by using voice recognition is provided. The method includes steps of: (a) a telematics server, if a text command signal converted from a voice command signal for a control of a vehicle from a voice input device and a user's voice sample are acquired from a voice recognition service-providing device, analyzing the user's voice sample; and (b) the telematics server, if the user's voice sample satisfies at least one preset condition, allowing the vehicle to be controlled according to the voice command signal by supporting a telematics device placed in the vehicle to run a telematics API corresponding to the text command signal. 1. A method for providing a telematics service by using voice recognition , comprising steps of:(a) a telematics server, if a text command signal converted from a voice command signal for a control of a vehicle from a voice input device and a user's voice sample are acquired from a voice recognition service-providing device, analyzing the user's voice sample; and(b) the telematics server, if the user's voice sample satisfies at least one preset condition, allowing the vehicle to be controlled according to the voice command signal by supporting a telematics device placed in the vehicle to run a telematics API corresponding to the text command signal.2. The method of claim 1 , before the step of (a) claim 1 , further comprising steps of:(a01) the telematics server, if a link establishing request is received from the voice recognition service-providing device, sending a request for the user's voice sample to the voice recognition service-providing device and acquiring it therefrom; and(a02) the telematics server managing the acquired user's voice sample to be corresponding to the user's information, creating a token ID corresponding to the user by referring to the user's voice sample, the user's information, and the vehicle's information and transmitting the created token ID to the voice recognition ...

GENERATING DIALOGUE BASED ON VERIFICATION SCORES

An example apparatus for generating dialogue includes an audio receiver to receive audio data including speech. The apparatus also includes a verification score generator to generate a verification score based on the audio data. The apparatus further includes a user detector to detect that the verification score exceeds a lower threshold but does not exceed a higher threshold. The apparatus includes a dialogue generator to generate dialogue to solicit additional audio data to be used to generate an updated verification score in response to detecting that the verification score exceeds a lower threshold but does not exceed a higher threshold. 1. An apparatus for generating dialogue , comprising:an audio receiver to receive audio data comprising speech;a verification score generator to generate a verification score based on the audio data;a user detector to detect that the verification score exceeds a lower threshold but does not exceed a higher threshold; anda dialogue generator to generate a dialogue to solicit additional audio data to be used to generate an updated verification score in response to detecting that the verification score exceeds a lower threshold but does not exceed a higher threshold.2. The apparatus of claim 1 , comprising a key phrase detector to detect a key phrase in the audio data claim 1 , wherein the verification score generator is to generate a verification score based on the audio data in response to the detection of the key phrase.3. The apparatus of claim 1 , comprising a speaker scorer to generate a speaker verification score based on the audio data and a speaker model claim 1 , wherein the verification score is at least in part based on the speaker verification score.4. The apparatus of claim 1 , comprising a speaker scorer to generate a speaker verification score based on the audio data and a speaker model claim 1 , wherein the speaker scorer is to calculate a text-dependent score based on the key phrase and a text-independent score ...

SPEAKER DIARIZATION WITH CLUSTER TRANSFER

Methods, computer program products, and systems are presented. The methods include, for instance: obtaining the media file with a speech and identifying speakers on clusters separated by disfluencies and change of speakers. Clusters are re-segmented rearranged during diarization. Speaker identifications for the clusters in the media file is produced. 1. A computer implemented method comprising:obtaining a media file having a speech by one or more speaker;stratifying the media file in order into a plurality of sessions at points of respective disfluencies in the speech;initializing one or more cluster space including one or more cluster, wherein the one or more cluster space respectively corresponds to the one or more speaker, wherein the one or more cluster results from identifying respective speaker of a predetermined number of session from the plurality of sessions;generating a cluster, wherein the generating a cluster includes identifying a speaker of a next session;determining a cluster action for the cluster based on a cluster epicenter;performing the cluster action from the determining on the one or more cluster space;bootstrapping the one or more cluster space resulting from the performing;generating another cluster by identifying speaker corresponding to another session from rest of the sessions; andproducing speaker identifications respective to each cluster from the generating.2. The computer implemented method of claim 1 , wherein the cluster action is a Removal action that changes boundaries between clusters claim 1 , wherein according to the Removal action a certain cluster is removed based on the certain cluster not including discernible speech.3. The computer implemented method of claim 1 , wherein the method includes applying a first set of clusters to a machine learning structure for learning by the machine learning structure claim 1 , the machine learning structure for use in returning cluster actions claim 1 , wherein the method includes applying ...

SPEECH PROCESSING APPARATUS, METHOD, AND PROGRAM

The speech processing apparatus includes an air microphone speech recognition unit which recognizes speech from an air microphone acquiring speech through air, a wearable microphone speech recognition unit which recognizes speech from a wearable microphone a sensing unit which measures environmental conditions, a weight decision unit which calculates the weights for recognition results of the air microphone speech recognition unit and the wearable microphone speech recognition unit on the basis of the environmental conditions, and a combination unit which combines the recognition results outputted from the air microphone speech recognition unit and the wearable microphone speech recognition unit using the weights. 1. A speech processing apparatus comprising:an air microphone speech recognition unit which recognizes speech from an air microphone acquiring speech through air,an wearable microphone speech recognition unit which recognizes speech from a wearable microphone,a sensing unit which measures environmental conditions including at least a distance between the air microphone and a speaker,an weight decision unit which calculates the weights for recognition results of the air microphone speech recognition unit and the wearable microphone speech recognition unit on the basis of the environmental conditions, anda combination unit which combines the recognition results outputted from the air microphone speech recognition unit and the wearable microphone speech recognition unit, using the weights.2. The speech processing apparatus according to claim 1 ,wherein the weight decision unit determines the weight for the recognition results of the wearable microphone speech recognition unit, in accordance with the distance between the air microphone and the speaker.3. The speech processing apparatus according to claim 2 ,wherein the weight for the recognition results of the air microphone speech recognition unit is monotonically non-decreasing functions, with respect to the ...

Voice-Controlled Management of User Profiles

A management of user profiles comprises calculating, for an audio segment, a user confidence measure representing a probability that the audio segment comprises speech of a user and a group confidence measure representing a probability that the audio segment comprises speech of a group of users. A user profile is then managed based on a comparison between the user confidence measure and a user confidence threshold and between the group confidence measure and a group confidence threshold. The embodiments thereby achieve an efficient voice-controlled user profile management by utilizing a layered approach that provides user profiles for group of users as fallback when the identity of the speaking user can not accurately be recognized. 126-. (canceled)27. A method of managing user profiles , the method comprising:calculating, for an audio segment, a user confidence measure representing a probability that the audio segment comprises speech of a user;calculating, for the audio segment, a group confidence measure representing a probability that the audio segment comprises speech of a group of users; andmanaging a user profile based on a comparison between the user confidence measure and a user confidence threshold and between the group confidence measure and a group confidence threshold.28. The method of claim 27 , wherein the group of users has common voice characteristics.29. The method of claim 27 , wherein the calculating the user confidence measure comprises:calculating, for the audio segment and for each user of a set of users, a respective user confidence measure representing a respective probability that the audio segment comprises speech of the user; andselecting a user confidence measure representing a highest probability among the respective calculated user confidence measures.30. The method of claim 27 , wherein the calculating the group confidence measure comprises:calculating, for the audio segment and for each group of users of a set of groups of users, a ...

COMPUTER PLATFORM AND METHOD FOR SECURELY EXCHANGING CONFIDENTIAL DATA AND GENERATING LEGAL DOCUMENTS

A system and method for securely exchanging confidential data and compiling legal documents, and performing particular legal actions using the confidential data, the documents being compiled based on features such as user location and verified user identity. 1. A computer-implemented platform for providing secure exchange of confidential data , comprising:a user database including at least one user profile, the user profile including user contact details and user identification data;a verification module for verifying the identity of a user attempting to access the platform, said verification module being configured to utilize biometric data to verify the user by comparing the biometric data against user biometric data stored in said user profile;a legal database including data useable according to legal requirements of a specific legal jurisdiction;a geographical engine configured to utilize geographical location data associated with the user's computing device and tag the user as being associated with a specific legal jurisdiction; anda compiler configured, in response to a user inquiry, to compile a legal document compatible according to specific legal standards of the identified jurisdiction associated with the user based on the geographical location of the user's computing device determined by said geographical engine.2. The platform of claim 1 , wherein the verification module is configured to use facial recognition to identify the user.3. The platform of claim 1 , wherein the verification module is configured to use voice recognition to identify the user.4. The platform of claim 1 , wherein said compiler is configured to utilize historical behavioral data of the user and user personal data to compile supplemental or ancillary legal documents identified as being ordinarily filed in conjunction with the legal document being compiled for the user.5. The platform of claim 1 , wherein said compiler is configured to consult at least one independent legal database ...

Auto-completion for Gesture-input in Assistant Systems

In one embodiment, a method includes receiving an initial input in a first modality from a first user from a client system associated with the first user, determining one or more intents corresponding to the initial input by an intent-understanding module, generating one or more candidate continuation-inputs based on the one or more intents, where the one or more candidate continuation-inputs are in one or more candidate modalities, respectively, and wherein the candidate modalities are different from the first modality, and sending instructions for presenting one or more suggested inputs corresponding to one or more of the candidate continuation-inputs to the client system. 1. A method comprising , by one or more computing systems:receiving, from a client system associated with a first user, an initial input from the first user, wherein the initial input is in a first modality;determining, by an intent-understanding module, one or more intents corresponding to the initial input;generating, based on the one or more intents, one or more candidate continuation-inputs, where the one or more candidate continuation-inputs are in one or more candidate modalities, respectively, and wherein the candidate modalities are different from the first modality; andsending, to the client system, instructions for presenting one or more suggested inputs corresponding to one or more of the candidate continuation-inputs.2. The method of claim 1 , wherein the first modality comprises one of audio claim 1 , text claim 1 , image claim 1 , video claim 1 , motion claim 1 , or orientation.3. The method of claim 2 , wherein the first modality comprises motion claim 2 , and wherein the initial input comprises a gesture.4. The method of claim 2 , wherein the first modality comprises orientation claim 2 , and wherein the initial input comprises a gaze on an object.5. The method of claim 1 , further comprising:determining that the first user needs one or more suggested inputs.6. The method of ...

METHOD AND DEVICE FOR TRANSFORMING FEATURE VECTOR FOR USER RECOGNITION

A method of converting a feature vector includes extracting a feature sequence from an audio signal including utterance of a user; extracting a feature vector from the feature sequence; acquiring a conversion matrix for reducing a dimension of the feature vector, based on a probability value acquired based on different covariance values; and converting the feature vector by using the conversion matrix. 1. A method of converting a feature vector , the method comprising:extracting a feature sequence from an audio signal including utterance of a user;extracting a feature vector from the feature sequence;acquiring a conversion matrix for reducing a dimension of the feature vector, based on a probability value acquired based on different covariance values; andconverting the feature vector by using the conversion matrix.2. The method of claim 1 , wherein the conversion matrix is a heteroscedastic linear discriminant analysis (HLDA).3. The method of claim 1 , wherein the acquiring of the conversion matrix comprises acquiring a useful dimension p of the conversion matrix claim 1 , based on accumulated energy for each dimension of a variance matrix for an intra-class covariance matrix of each speaker.4. The method of claim 1 , wherein the feature vector is an i-vector that is acquirable by joint factor analysis.5. The method of claim 1 , further comprising:performing scoring on a feature vector resulting from the conversion and a feature vector of each state, at least once; andidentifying the user, based on a result of the scoring.6. A device for converting a feature vector claim 1 , the device comprising:a receiver which receives an audio signal including utterance of a user; anda controller which extracts a feature sequence from the audio signal, extracts a feature vector from the feature sequence, acquires a conversion matrix for reducing a dimension of the feature vector, based on a probability value acquired based on different covariance values, and converts the feature ...

AIR-CONDITIONER CONTROLLER

An air-conditioner controller that controls an operation of an air conditioner includes: a storage unit that stores, for each user, voiceprint data that is data indicating a voiceprint of a user and personal data that is data indicating a feature of the user; and a control unit that compares voice data that is data of a user's voice detected in an air-conditioning area that is an area subject to air-conditioning control of the air conditioner with the voiceprint data, and, when there is voiceprint data similar to the voice data, presents a question based on the personal data to identify a user in the air-conditioning area on the basis of an answer acquired from the user in the air-conditioning area. 1. An air-conditioner controller that controls an operation of an air conditioner , the air-conditioner controller comprising:a storage unit to store, for each user, voiceprint data that is data indicating a voiceprint of a user, and personal data that is data indicating a feature of a user; anda control unit to compare voice data that is data of a voice detected in an air-conditioning area that is an area subject to air-conditioning control of the air conditioner with the voiceprint data, and to, when there is voiceprint data similar to the voice data, present a question based on the personal data to identify a user in the air-conditioning area on the basis of an answer acquired from the user in the air-conditioning area.2. The air-conditioner controller according to claim 1 , whereinthe personal data includes information indicating a characteristic with respect to temperature, andthe control unit determines an air-conditioning control content of the air conditioner using personal data of an identified user, and instructs the air conditioner on the air-conditioning control content.3. The air-conditioner controller according to claim 2 , whereinthe control unit presents a question about an air-conditioning state to the identified user, corrects the personal data of the ...

METHOD AND APPARATUS FOR PERFORMING SPEAKER RECOGNITION

Embodiments of the present invention perform speaker identification and verification by first prompting a user to speak a phrase that includes a common phrase component and a personal identifier. Then, the embodiments decompose the spoken phrase to locate the personal identifier. Finally, the embodiments identify and verify the user based on the results of the decomposing. 1identifying a user as a function of a decomposed single spoken phrase that includes a personal identifier within the spoken phrase and a common phrase component within the spoken phrase, the identifying comprising comparing the personal identifier against previously stored identifying information;verifying the user as a function of the decomposed single spoken phrase, the verifying comprising comparing the common phrase component against one or more previously stored voice prints associated with at least a subgroup of all users represented within the one or more previously stored voice prints; andoutputting an indicator, if identified and verified, that enables the user to gain access to a computing system.. A method of performing automated access control using speaker recognition performed via an automated user-machine interaction, the method comprising: This application is a continuation of U.S. application Ser. No. 14/489,996, filed on Sep. 18, 2014. The entire teachings of the above application(s) are incorporated herein by reference.Achieved advances in speech processing and media technology have led to a wide use of automated user-machine interaction across different applications and services. Using an automated user-machine interaction approach, businesses may provide customer services and other services with relatively inexpensive cost. Some such services may employ speaker recognition, i.e., identification and verification of the speaker.Embodiments of the present invention provide methods and systems for speaker recognition. According to an embodiment of the present invention, a method ...

SEAMLESS TEXT-DEPENDENT ENROLLMENT

Methods and systems for transforming a text-independent enrolment of a customer in a self-service system into a text-dependent enrolment are provided. A request for authentication of a customer that is enrolled in the self-service system with a text-independent voice print is received. A request is transmitted to the customer to repeat a passphrase and the customer's response is received as an audio stream of the passphrase. The customer is authenticated by comparing the audio stream of the passphrase against the text-independent voice print and if the customer is authenticated then a text-dependent voice print is created based on the passphrase, otherwise discard the audio stream of the passphrase. 1. A computer-implemented method for transforming a text-independent enrolment of a customer in a self-service system into a text-dependent enrolment , the method comprising:receiving a request for authentication of the customer, the customer is enrolled in the self-service system with a text-independent voice print;transmitting a request to the customer to repeat a passphrase;receiving an audio stream of the passphrase;authenticating the customer by comparing the audio stream of the passphrase against the text-independent voice print; andif the customer is authenticated then creating a text-dependent voice print based on the passphrase, otherwise discard the audio stream of the passphrase.2. The computer-implemented method of further comprising upon receipt of a subsequent request for authentication of the customer claim 1 , transmitting a request to the customer to repeat the passphrase claim 1 , receiving another audio stream of the passphrase claim 1 , and authenticating the customer by comparing the another audio stream of the passphrase with the text-dependent voice print.3. The computer-implemented method of wherein authenticating the customer by comparing the another audio stream of the passphrase with the text-dependent voice print further comprising ...

BOT-BASED DATA COLLECTION FOR DETECTING PHONE SOLICITATIONS

One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data. 1. A method comprising: collecting training data;', classifying each portion of the training data as one of poison data or truthful training data based on content of the portion and one or more learned detection models for detecting poisoned data; and', 'filtering the training data to remove any portion of the training data that is classified as poison data; and, 'protecting the training data against an adversary attempting to poison the training data by, 'training the machine learning model based on the filtered training data., 'decreasing a likelihood of a misclassification from a machine learning model by2. The method of claim 1 , wherein collecting training data comprises:answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot configured to engage in one or more conversations with one or more callers who initiate the one or more incoming phone calls; andrecording the one or more conversations;wherein the training data comprises the one or more recorded conversations.3. The method of claim 2 , wherein the bot is configured to utilize a voice recording that impersonates an individual belonging to a type of demographic targeted by the one or more callers.4. The method of claim 2 , wherein the bot is configured to dynamically converse with the one or more callers based on a conversation template including one or more learned ...

SYSTEM AND METHOD FOR AUGMENTED REALITY VIDEO CONFERENCING

A system includes a plurality of capturing devices and a plurality of displaying devices. The capturing devices and the displaying devices can be communicatively connected to a server. The server can receive captured data from the capturing devices and transform the data into a digitized format. At least one of the capturing devices can record a video during a meeting and the capturing device can transmit the captured video to the server as a video feed. The video feed can show an area that includes handwritten text, e.g., a whiteboard. The server can receive the video feed from the capturing device and perform various processes on the video. For example, the server can perform a voice recognition, text recognition, handwriting recognition, face recognition and/or object recognition technique on the captured video. 120-. (canceled)21. A method comprising:receiving, at a server, a first video feed from a first camera;{'claim-text': ['extract a first text from a first segment of the first video feed; and', 'identify a first person;'], '#text': 'processing, using a processor of the server, the first video feed to:'}receiving, at the server, a second video feed from a second camera;{'claim-text': ['extract a second text from a second segment of the second video feed; and', 'identify a second person;'], '#text': 'processing, using the processor of the server, the second video feed to:'}{'claim-text': ['the first summary is displayed in association with the first person and the second summary is displayed in association with the second person; and', 'the first summary is selectable to display a first media file and the second summary is selectable to display a second media file.'], '#text': 'generating, using the processor of the server, a slide showing a first summary of the first text and a second summary of the second text, wherein:'}220. The method of claim , further comprising processing , using the processor of the server , the first video feed to extract a first ...

Mobile Terminal And Hub Apparatus For Use In A Video Communication System

A hub apparatus () is designated to be used in a video communication system comprising the hub apparatus () and a plurality of mobile terminals (-) configured to be wirelessly connectable to the hub apparatus (). The hub apparatus () comprises: a receiving unit () configured to receive from each mobile terminal () of the plurality of mobile terminals (-) a video stream, a current speaker indicator to indicate whether the user of the mobile terminal is speaking and an association information which associates the current speaker indicator transmitted by the mobile terminal with the video stream transmitted from such mobile terminal (), and a generation unit () operatively connected to said receiving unit () and configured to generate an output video communication stream () based on the plurality of video streams received from each mobile terminal () of the plurality of mobile terminals (-), on the plurality of current speaker indicators received from each mobile terminal () of the plurality of mobile terminals (-) and on the plurality of association information received from each mobile terminal () of the plurality of mobile terminals (-). 1. A mobile terminal comprising:a transmission unit configured to transmit to a hub a video stream generated from an input video signal, and wherein a timing parameter is received from the hub indicating a frequency interval of how frequently a current speaker indicator must be repeatedly generated;a storage configured to store a voice timbre pattern model of a user of the mobile terminal;wherein the transmission unit is configured to transmit to the hub, a current speaker indicator in accordance with the frequency interval and an association information which associates the current speaker indicator to the video stream; anda processing unit configured to extract a voice timbre pattern model from an input audio signal to calculate a correlation parameter percentage value based on a probability of similarity between the extracted ...

SYSTEMS AND METHODS FOR IDENTIFYING USERS OF DEVICES AND CUSTOMIZING DEVICES TO USERS

A system and method for identifying a user of a device includes comparing audio received by a device with acoustic fingerprint information to identify a user of the device. Image data, video data and other data may also be used in the identification of the user. Once the user is identified, operation of the device may be customized based on the user. Further, once the user is identified, data can be associated with the user, for example, usage data, location data, gender data, age data, dominant hand data of the user, and other data. This data can then be used to further customize the operation of the device to the specific user. 1. A computer-implemented method , comprising:receiving, over a network, first audio data corresponding to a microphone of a first device, the first audio data representing a voice of a user;determining, using at least one remote device, a user profile corresponding to first audio data by processing the first audio data with respect to voice fingerprint data in the user profile, the user profile associated with at least one adjusted operating parameter; andsending, over the network, an instruction to the first device to cause the first device to be operated using the adjusted operating parameter.2. The computer-implemented method of claim 1 , further comprising:using the first audio data to determine a location of the first device,wherein the adjusted operating parameter is determined based at least in part on the location.3. The computer-implemented method of claim 1 , further comprising:determining personalized information associated with the identity of the user;associating, by the at least one remote device, the personalized information with the first device;after associating the personalized information with the first device, determining the user is no longer operating the first device; andafter determining the user is no longer operating the first device, disassociating, by the at least one remote device, the personalized information ...

ANCHORED SPEECH DETECTION AND SPEECH RECOGNITION

A system configured to process speech commands may classify incoming audio as desired speech, undesired speech, or non-speech. Desired speech is speech that is from a same speaker as reference speech. The reference speech may be obtained from a configuration session or from a first portion of input speech that includes a wakeword. The reference speech may be encoded using a recurrent neural network (RNN) encoder to create a reference feature vector. The reference feature vector and incoming audio data may be processed by a trained neural network classifier to label the incoming audio data (for example, frame-by-frame) as to whether each frame is spoken by the same speaker as the reference speech. The labels may be passed to an automatic speech recognition (ASR) component which may allow the ASR component to focus its processing on the desired speech.

MACHINE LEARNING FOR AUTHENTICATING VOICE

A machine learning multi-dimensional acoustic feature vector authentication system, according to an example of the present disclosure, builds and trains multiple multi-dimensional acoustic feature vector machine learning classifiers to determine a probability of spoofing of a voice. The system may extract an acoustic feature from a voice sample of a user. The system may convert the acoustic feature into multi-dimensional acoustic feature vectors and apply the multi-dimensional acoustic feature vectors to the multi-dimensional acoustic feature vector machine learning classifiers to detect spoofing and determine whether to authenticate a user. 1. A machine learning multi-dimensional acoustic feature vector authentication system comprising:at least one processor to execute machine readable instructions stored on at least one non-transitory computer readable medium; 'wherein the plurality of multi-dimensional acoustic feature vector machine learning classifiers comprise convolutional neural networks trained to identify multi-dimensional acoustic feature vectors;', 'at least one data storage to store a plurality of multi-dimensional acoustic feature vector machine learning classifiers,'} extract at least one acoustic feature from a voice sample of a user;', 'convert the acoustic feature into a plurality of multi-dimensional acoustic feature vectors;', 'apply each multi-dimensional acoustic feature vector in the plurality of multi-dimensional acoustic feature vectors to a corresponding multi-dimensional acoustic feature vector machine learning classifier from the plurality of multi-dimensional acoustic feature vector machine learning classifiers;', 'determine a probability of spoofing for each multi-dimensional acoustic feature vector from an output of the corresponding multi-dimensional acoustic feature vector machine learning classifier;', 'determine an overall probability of spoofing for the voice sample, based on the probability of spoofing for each multi-dimensional ...

ENTERING OF HUMAN FACE INFORMATION INTO DATABASE

A processor chip circuit is provided, which is used for entering human face information into a database and includes a circuit unit configured to perform the steps of: videoing one or more videoed persons and extracting human face information of the one or more videoed persons from one or more video frames during the videoing; recording a voice of at least one of the one or more videoed persons during the videoing; performing semantic analysis on the recorded voice so as to extract respective information therefrom; and associating the extracted information with the human face information of the videoed person who has spoken the extracted information, and entering the associated information into the database. 1. A processor chip circuit for entering human face information into a database , comprising:a circuit unit coupled with an auxiliary wearable device configured for being worn by a visually impaired person, the circuit unit being configured to perform, from the auxiliary wearable device, the steps of:videoing one or more videoed persons and extracting human face information of the one or more videoed persons from one or more video frames during the videoing;recording a voice of at least one of the one or more videoed persons during the videoing, wherein the voice of the at least one videoed person comprises identity information of a speaker that is spoken by the speaker;performing semantic analysis on the recorded voice so as to extract respective information therefrom, wherein the extracted respective information comprises the identity information of the speaker; andassociating the extracted information with the human face information of the videoed person who has spoken the extracted information, and entering the associated information into the database,wherein the circuit unit is further configured to perform, from the auxiliary wearable device, the step of:accessing, during a conversation participated by the visually impaired person and at least one of the ...

SECURE NONSCHEDULED VIDEO VISITATION SYSTEM

Described are methods and systems in which the censorship and supervision tasks normally performed by secured facility personnel are augmented or automated entirely by a Secure Nonscheduled Video Visitation System. In embodiments, the Secure Nonscheduled Video Visitation System performs voice biometrics, speech recognition, non-verbal audio classification, fingerprint and other biometric authentication, image object classification, facial recognition, body joint location determination analysis, and/or optical character recognition on the video visitation data. The Secure Nonscheduled Video Visitation utilizes these various analysis techniques in concert to determine if all rules and regulations enforced by the jurisdiction operation the secured facility are being followed by the parties to the video visitation session. 1. A video visitation central processing platform comprising: connect a video visitation session between a local video communication device and a remote video communication device;', 'conduct a first analysis on video visitation data to identify at least one individual party to the video visitation session;', 'conduct a second analysis on the video visitation data to detect the presence of a disallowed data item in the video visitation data; and', 'control the state of the video visitation session based on the first analysis and the second analysis., 'one or more processors and/or circuits configured to2. The video visitation central processing platform of claim 1 , wherein the first analysis includes identifying a speaker in audio data of the video visitation session using voice biometrics.3. The video visitation central processing platform of claim 1 , wherein the second analysis includes recognizing spoken words in audio data of the video visitation data using speech recognition.4. The video visitation central processing platform of claim 1 , wherein the second analysis includes classifying non-verbal audio in audio data of the video visitation ...

HEAD MOUNTED DISPLAY DEVICE FOR USE IN A MEDICAL FACILITY

A head-mounted display device for interface with a medical device configured to perform an invasive procedure on a patient, such as a blood component collection, an infusion, a feeding operation, etc. 171-. (canceled)72. A head-mounted display device for interface with a medical device configured to perform an invasive procedure on a patient , comprising:a frame configured to be mounted on a person's head;a display;a sensor;a wireless transceiver configured to communicate with a network; anda processing circuit coupled to the frame, the display, the sensor and the wireless transceiver, wherein the processing circuit is configured to receive at least one of sound and image data from the sensor, wherein the at least one of sound and image data is associated with a person in the vicinity of the device, to compare the at least one of sound and image data to the at least one of sound and image data associated with the patient who is to receive the invasive procedure using the medical device, and to generate output data based on the comparison.73. The device of claim 72 , wherein the sound data comprises a sample of a voice of the person in the vicinity of the device.74. The device of claim 73 , wherein the processing circuit is configured to use voice recognition to do the comparison.75. The device of claim 72 , wherein the image data comprises an image of the person in the vicinity of the device.76. The device of claim 75 , wherein the processing circuit is configured to use facial recognition to do the comparison.77. The device of claim 75 , wherein the device is configured to acquire the image of the person in the vicinity of the device while the person in the vicinity of the device is wearing the device.78. The device of claim 75 , wherein the processing circuit is configured to use a retinal scan to do the comparison.79. The device of claim 72 , wherein both sound and image data associated with the person in the vicinity of the device are compared to sound and image ...

FAST SPEAKER RECOGNITION SCORING USING I-VECTOR POSTERIORS AND PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS

A method for performing speaker recognition comprises: estimating respective uncertainties of acoustic coverage of respective speech utterance(s) by first and second speakers, the acoustic coverage representing respective sounds used by the speakers when speaking; representing the respective uncertainties of acoustic coverage in a manner that allows for efficient memory usage by discarding dependencies between uncertainties of different sounds for the speakers; representing the respective uncertainties of acoustic coverage in a manner that allows for efficient computation by representing an inverse of the respective uncertainties of acoustic coverage and then discarding the dependencies between the uncertainties of different sounds for the speakers; and computing a score between the speech utterance(s) by the speakers in a manner that leverages the respective uncertainties of the acoustic coverage during the comparison, the score being indicative of a likelihood that the speakers are the same speaker. 1. A method of speaker recognition , the method comprising:estimating respective uncertainties of acoustic coverage of at least one speech utterance by a first speaker and at least one speech utterance by a second speaker, the acoustic coverage representing respective sounds used by the first speaker and by the second speaker when speaking;representing the respective uncertainties of acoustic coverage in a manner that allows for efficient memory usage by discarding dependencies between uncertainties of different sounds for the first speaker and for the second speaker;representing the respective uncertainties of acoustic coverage in a manner that allows for efficient computation by representing an inverse of the respective uncertainties of acoustic coverage and then discarding the dependencies between the uncertainties of different sounds for the first speaker and for the second speaker; andcomputing a score between the at least one speech utterance by the first speaker ...

AUTHENTICATION TECHNIQUES INCLUDING SPEECH AND/OR LIP MOVEMENT ANALYSIS

A system, apparatus, method, and machine readable medium are described for performing eye tracking during authentication. For example, one embodiment of a method comprises: receiving a request to authenticate a user; presenting one or more screen layouts to the user; capturing a sequence of images which include the user's eyes as the one or more screen layouts are displayed; and (a) performing eye movement detection across the sequence of images to identify a correlation between motion of the user's eyes as the one or more screen layouts are presented and an expected motion of the user's eyes as the one or more screen layouts are presented and/or (b) measuring the eye's pupil size to identify a correlation between the effective light intensity of the screen and its effect on the user's eye pupil size; capturing audio of the user's voice; and performing voice recognition techniques to determine a correlation between the captured audio of the user's voice and one or more voice prints. 1. A method comprising:receiving a request to authenticate a user;presenting one or more screen layouts to the user;capturing a sequence of images which include the user's eyes as the one or more screen layouts are displayed; and (a) performing eye movement detection across the sequence of images to identify a correlation between motion of the user's eyes as the one or more screen layouts are presented and an expected motion of the user's eyes as the one or more screen layouts are presented and/or (b) measuring the eye's pupil size to identify a correlation between the effective light intensity of the screen and its effect on the user's eye pupil size;capturing audio of the user's voice; andperforming voice recognition techniques to determine a correlation between the captured audio of the user's voice and one or more voice prints.2. The method as in further comprising:performing facial recognition to identify a correlation between one or more images of the user's face and facial ...

SYSTEM, METHOD, AND RECORDING MEDIUM FOR FIXED-WING AIRCRAFT ADVERTISEMENT USING LOCALLY SAMPLED WORD LISTENING

A fixed-wing aircraft advertisement method, system, and non-transitory computer readable medium for a fixed-wing aircraft, include a user observing circuit configured to observe a plurality of users to identify a speaking user, a word identifying circuit configured to identify a keyword profile from words of the speech of the speaking user, and an advertisement selecting and delivering circuit configured to select an advertisement to deliver via the fixed-wing aircraft based on the advertisement being associated with the keyword profile. 1. A fixed-wing aircraft advertisement system for a fixed-wing aircraft , the system comprising:a user observing circuit configured to observe a plurality of users to identify a speaking user;a word identifying circuit configured to identify a keyword profile from words of the speech of the speaking user; andan advertisement selecting and delivering circuit configured to select an advertisement to deliver via the fixed-wing aircraft based on the advertisement being associated with the keyword profile.2. The system of claim 1 , wherein the user observing circuit identifies the speaking user without determining an individual identity of the speaking user.3. The system of claim 1 , wherein the user observing circuit identifies a plurality of speaking users from the plurality of users based on the plurality of speaking users having a highest lip movement rate.4. The system of claim 1 , further comprising an audio recognition controlling circuit configured to control an audio detection device on the fixed-wing aircraft to point at the speaking user to detect the words of the speaking user.5. The system of claim 1 , wherein the user observing circuit identifies the speaking user by:detecting a face of each of the plurality of users;detecting facial landmarks of the plurality of users;tracking the facial landmarks surrounding lips of each of the plurality of users to determine a movement rate of the lips of the each of the plurality of ...

SECURITY SURVEILLANCE VIA THREE-DIMENSIONAL AUDIO SPACE PRESENTATION

Embodiments are directed to using a three-dimensional sound space to analyze security surveillance information. According to one embodiment, the three-dimensional sound space can comprise part of a security surveillance system in which sound sources related to security surveillance information can be presented and a user can efficiently navigate even a large number of sound sources in the three-dimensional sound space. Effective audio surveillance relies on the ability of the surveillance personnel to efficiently identify calls that need further analysis and calls that need no further analysis without introducing too many false negative or false positive conditions. Utilization of three-dimensional space described herein can increase the ease with which security analysts review audio content and identify relevant audio content that requires further analysis. 1. A method comprising:collecting, by a processor, security surveillance information from one or more data sources, the security surveillance information comprising at least in part audio data from at least one of the one or more data sources;processing, by the processor, the collected security surveillance information into a plurality of sound sources based on one or more attributes of the security surveillance information; andpresenting, by the processor, the plurality of sound sources in a three-dimensional sound space having the plurality of sound sources playing at a same time, wherein each of the plurality of sound sources is assigned a respective location in the three-dimensional sound space relative to one another, and wherein a user is assigned a current location in the three-dimensional sound space relative to each respective location.2. The method of claim 1 , wherein the security surveillance information further comprises non-audio data from at least one or the one or more data sources and wherein processing the collected security surveillance information into a plurality of sound sources further ...

SPEAKER RECOGNITION

This application describes methods and apparatus for generating a prompt to be presented to a user for the user to vocalise as part of speaker recognition. An apparatus according to an embodiment has a selector for selecting at least one vocal prompt element to form at least part of said prompt from a predetermined set of a plurality of vocal prompt elements. The selector is configured to select the vocal prompt element based, at least partly, on an indication of the operating conditions for the biometric speaker recognition, for example background noise. The prompt is selected to be one which will provide a good likelihood of discrimination between users when vocalised and used for speaker recognition in the current operating conditions. The prompt may be issued as part of a verification process for an existing user or an enrolment process for an enrolling user. 1. An apparatus for generating a prompt to be vocalised by a user for biometric speaker recognition comprising:a selector for selecting at least one vocal prompt element to form at least part of said prompt from a predetermined set of a plurality of vocal prompt elements;wherein the selector is configured to select the vocal prompt element based, at least partly, on an indication of the operating conditions for the biometric speaker recognition.2. The apparatus as claimed in wherein the selector is configured to select the vocal prompt element based on respective discrimination scores for the vocal prompt elements wherein at least some discrimination scores vary according to the indication of operating conditions for the biometric speaker recognition.3. The apparatus as claimed in wherein said set of plurality of vocal prompt elements comprises a plurality of predefined subsets of vocal prompt elements and the selector is configured to select the voice prompt from one of the subsets based on the indication of operating conditions.4. The apparatus as claimed in wherein the voice prompt elements are ...

Speech endpointing based on word comparisons

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value.

Neural Networks for Speaker Verification

Systems, methods, devices, and other techniques for training and using a speaker verification neural network. A computing device may receive data that characterizes a first utterance. The computing device provides the data that characterizes the utterance to a speaker verification neural network. Subsequently, the computing device obtains, from the speaker verification neural network, a speaker representation that indicates speaking characteristics of a speaker of the first utterance. The computing device determines whether the first utterance is classified as an utterance of a registered user of the computing device. In response to determining that the first utterance is classified as an utterance of the registered user of the computing device, the device may perform an action for the registered user of the computing device. 1. A computer-implemented method , comprising:receiving, by a computing device, data that characterizes a first utterance; (i) differences among speaker representations generated by the speaker verification neural network from training utterances of the training speaker within the batch, and', '(ii) for each first speaker representation generated from a training utterance of the training speaker within the batch, a similarity between the first speaker representation and a second speaker representation for a particular different training speaker represented in the batch, the particular different training speaker selected from among the multiple training speakers represented in the batch based on a distance between the first speaker representation generated from the training utterance of the training speaker and the second speaker representation for the particular different training speaker, the second speaker representation determined based on multiple training utterances of the particular different training speaker;, 'providing, by the computing device, the data that characterizes the utterance to a speaker verification neural network, wherein ...

AUDIO PRIVACY BASED ON USER IDENTIFICATION

A method and apparatus for audio privacy may be based on user identification. An audio signal containing speech may be analyzed, identifying a user to which the speech belongs and determining a user class for the user. The speech may be uploaded to a remote device based on whether the user class for the user is a public user class or a private user class. This allows certain users to opt-out of having their speech uploaded through public networks. The user identification may be based on voice biometrics. 1. A method , comprising:receiving an audio input signal comprising speech;identifying a user based, at least in part, on characteristics of the speech;determining a user class for the user, wherein the user class comprises a privacy setting; andperforming an action based, at least in part, on the determined user class,wherein the step of performing an action is based, at least in part, on criteria defined for the determined user class regarding whether the speech is allowed by the user for transmission over a public network or disallowed by the user for transmission over the public network.2. The method of claim 1 , wherein the step of performing an action comprises uploading the speech to a remote system when allowed by the determined user class for the user.3. The method of claim 1 , wherein determining the user class for the user comprises classifying the user as one of a public user class and a private user class claim 1 , wherein the public user class allows uploading of speech to the remote system.4. (canceled)5. The method of claim 1 , wherein the step of performing an action is based claim 1 , at least in part claim 1 , on a destination of the speech on the public network.6. The method of claim 1 , wherein the step of uploading the speech comprises analyzing a portion of the speech to obtain an indication of a content of the speech; and uploading the speech when uploading of the indicated content is allowed by the determined user class for the user.7. The ...

Voice Control Processing Method and Apparatus

A voice control processing method and apparatus, where the method includes enabling, by a terminal in a data service disabled state, a data service after the terminal receives a voice instruction using a first application, where the first application is an application program used for voice control in the terminal, prohibiting, by the terminal, another application other than the first application in the terminal from using the data service, and controlling, by the terminal, the first application to execute the voice instruction using the data service, after the terminal enables the data service. The terminal in a data service disabled state receives the voice instruction. Then, the terminal enables the data service and prohibits another application from using the data service.

Speaker recognition based on vibration signals

An embodiment of a semiconductor package apparatus may include technology to acquire vibration information corresponding to a speaker, and identify the speaker based on the vibration information. Other embodiments are disclosed and claimed.

Biometric authentication of electronic signatures

At least one contemporaneous signature image is captured while a user generates an electronic signature for a document. When one or more contemporaneous signature images maps to a verification image, signature data representative of an electronic signature is associated with the document.

SPEECH ENDPOINTING BASED ON WORD COMPARISONS

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value. 1. (canceled)2. A computer-implemented method comprising:receiving, by one or more computing devices, audio data of an utterance;based on the audio data, determining, by the one or more computing devices, a first likelihood that the utterance is a complete utterance;generating, by the one or more computing devices, a transcription of the utterance;based on the transcription of the utterance, determining, by the one or more computing devices, a second likelihood that the utterance is a complete utterance; andbased on the first likelihood that the utterance is a complete utterance and the second likelihood that the utterance is a complete utterance, determining, by the one or more computing devices, whether to designate an endpoint of the utterance at an end of the audio data of the utterance.3. The method of claim 2 , wherein determining the first likelihood that the utterance is a complete utterance comprises:determining a period of time in the audio data of the utterance when an energy level is below a threshold energy level;comparing the period of time to a threshold time period; anddetermining the ...

Information processing method and device, multimedia device and storage medium

The present disclosure discloses an information processing method, a service providing system, and a computer storage medium. The method includes: assigning at least one first account for a multimedia device; assigning a plurality of second accounts associated with the first account for the multimedia device, each second account representing one user identifier; acquiring a voice instruction; determining a currently used second account according to the voice instruction; searching for user preference information associated with the currently used second account; and providing, based on the user preference information and service request information determined based on the voice instruction, a first service to the user identifier represented by the currently used second account.

Ambient Cooperative Intelligence System and Method

A method, computer program product, and computing system for initiating a session within an ACI platform; receiving an authentication request from a requester; and authenticating that the requester has the authority to access the ACI platform. 1. A computer-implemented method , executed on a computing device , comprising:initiating a session within an ACI platform;receiving an authentication request from a requester; andauthenticating that the requester has the authority to access the ACI platform.2. The computer-implemented method of wherein receiving an authentication request from a requester includes:receiving a verbal authentication request from the requester via a virtual assistant.3. The computer-implemented method of wherein receiving an authentication request from a requester includes:receiving a verbal command from the requester via a virtual assistant.4. The computer-implemented method of wherein receiving an authentication request from a requester includes:receiving a login request from the requester.5. The computer-implemented method of further comprising:if the requester is authenticated, allowing the requester to access the ACI platform; andif the requester is not authenticated, preventing the requester from accessing the ACI platform.6. The computer-implemented method of further comprising:if the requester is not authenticated, notifying the requester that they cannot access the ACI platform.7. The computer-implemented method of further comprising:if the requester is not authenticated, notifying a third party that the requester was prevented from accessing the ACI platform.8. The computer-implemented method of wherein authenticating that the requester has the authority to access the ACI platform includes:determining a user identity for the requester; andconfirming that the user identity has the authority to access the ACI platform.9. The computer-implemented method of wherein authenticating that the requester has the authority to access the ACI ...

VOICE-CONTROLLABLE IMAGE DISPLAY DEVICE AND VOICE CONTROL METHOD FOR IMAGE DISPLAY DEVICE

A voice-controllable image display device comprises: a memory unit for storing therein a database to which identified voice data is allocated and mapped for each execution unit area of a screen displayed through the display unit; a voice recognition unit for receiving an input of a user's voice; an information processing unit for searching the database and determining whether there is identified voice data corresponding to the user's voice when the voice recognition unit receives the user's voice; and a control unit for generating an input signal in the execution unit area to which the identified voice data is allocated if there is identified voice data corresponding to the user's voice as a result of the determination by the information processing unit. 1. A voice-controllable image display device having a display unit , the voice-controllable image display device comprising:a memory unit configured to store a database in which voice identification data is allocated and mapped to each execution unit area on a screen displayed through the display unit;a voice recognition unit configured to receive a user's voice as an input;an information processing unit configured to search the database and determine whether voice identification data corresponding to the user's voice is present when the voice recognition unit receives the user's voice; anda control unit configured to generate an input signal in an execution unit area to which the voice identification data is allocated when the information processing unit determines that the voice identification data corresponding to the user's voice is present, whereinthe database additionally stores voice control data corresponding to a control command for performing a specific screen control based on the execution unit area to which the voice identification data is allocated, when the voice control data is used in combination with the voice identification data,when the voice recognition unit receives a user's voice, the ...

LOCATION BASED VOICE RECOGNITION SYSTEM

Systems and methods for providing location based voice recognition include receiving, through a first microphone, an audio signal from a first user that includes an audio command requesting a service that requires user authorization before access to at least a portion of the service is granted. The user authorization is based on voice recognition (e.g., voice authentication and/or voice identification) of the audio signal. The source location of the audio signal is determined and a user location of the first user is determined. If the source location of the audio signal correlates with the user location, voice recognition on the audio signal may be performed. The first user may be authorized to access the service based on the voice recognition performed on the audio signal. 1. A voice recognition system , comprising:a first microphone configured to capture an audio signal from an environment surrounding the first microphone and convert the audio signal into an electrical signal;a non-transitory memory; and receiving, via the first microphone, an audio signal from a first user that includes an audio command requesting a service that requires user authorization before access to at least a portion of the service is granted;', 'determining a source location of the audio signal based on time of arrival of the audio signal at the first microphone;', 'determining a user location of the first user;', 'determining whether the source location of the audio signal correlates with the user location such that the source location and the user location are within a predetermined distance of each other;', 'performing, in response to determining the source location correlates with the user location, voice recognition on the audio signal; and', 'authorizing, based on the voice recognition performed on the audio signal, the first user to access the service., 'one or more hardware processors coupled to the non-transitory memory and the first microphone, wherein the one or more hardware ...

LOCATION BASED VOICE ASSOCIATION SYSTEM

Systems and methods for associating audio signals in an environment surrounding a voice-controlled system include receiving by a voice-controlled system through a microphone, an audio signal from a user of a plurality of users within an environment surrounding the microphone. The voice-controlled system determines a source location of the audio signal. The voice-controlled system determines a first user location of a first user and a second user location of a second user. The voice-controlled system then determines that the first user location correlates with the source location such that the source location and the first user location are within a predetermined distance of each other. In response, the voice-controlled system performs at least one security action associated with the first user providing the audio signal. 1. A voice association system , comprising:a microphone configured to capture an audio signal from an environment surrounding the microphone and convert the audio signal into an electrical signal;a non-transitory memory; and receiving, through the microphone, a first audio signal from a first user of a plurality of users within the environment;', 'determining a first source location of the first audio signal;', 'determining a first user location of the first user and a second user location of a second user; Подробнее

VOICE PRINT IDENTIFICATION PORTAL

Systems and methods providing for secure voice print authentication over a network are disclosed herein. During an enrollment stage, a client's voice is recorded and characteristics of the recording are used to create and store a voice print. When an enrolled client seeks access to secure information over a network, a sample voice recording is created. The sample voice recording is compared to at least one voice print. If a match is found, the client is authenticated and granted access to secure information. 118-. (canceled)19. A method of operating a voice analysis system , comprising:using a front end interface on a computer system that includes a microphone to initialize a voice analysis system for a user by inputting at least a first voice recording of the user via the microphone to be communicated over a network connection to a voice analysis computer system that analyzes and stores a template voiceprint for authentication of the user;using the front end interface to input a second voice recording of the user via the microphone to be communicated over the network connection to the voice analysis computer system; setting voice analysis constraints to a level associated with a speaker identification mode;', 'comparing the second voice recording to the template voiceprint, wherein the comparison is based at least in part on the constraints to determine if the second voice recording provides a positive match with a voice characteristic of the voice template, and if there is a positive match:', 'storing a representation of each second voice recording as part of the template voiceprint for the user;', 'using the voice analysis system to compare the second voice recording with each of the representations of each second voice recording stored as part of the template voiceprint fur the user associated with the positive match to determine that the second voice recording has not been used previously for authentication of the user; and', 'communicating over the ...

Method and Apparatus for Managing Graded Cipher

Provided are a method and apparatus for managing a graded cipher. The method includes that: a corresponding relationship between different security grades and corresponding voice passwords is established, herein the voice password corresponding to each security grade in the corresponding relationship is a part or all of a preset voice password; and a voice password is received from a user, and the obtained corresponding relationship is searched for the security grade corresponding to the voice password matched with the received voice password. 1. A method for managing a graded cipher , comprising:establishing a corresponding relationship between different security grades and corresponding voice passwords, wherein a voice password corresponding to each security grade in the corresponding relationship is a part or all of a preset voice password; andreceiving a voice password from a user, and searching the obtained corresponding relationship for a security grade corresponding to a voice password matched with the received voice password.2. The method according to claim 1 , wherein when a security grade in the corresponding relationship is higher claim 1 , a length of a voice password corresponding to the security grade is larger.3. The method according to claim 1 , wherein the establishing a corresponding relationship between different security grades and corresponding voice passwords comprises:acquiring the preset voice password and a security grade number in advance; andacquiring a voice password, of which a length is (N-i)/N of a length of the preset voice password, from the preset voice password, and setting a corresponding relationship between the obtained voice password and an ith security grade;wherein N is the security grade number, and i is an integer more than or equal to 0.4. The method according to claim 3 , wherein the setting a corresponding relationship between the obtained voice password and an ith security grade comprises:extracting a voiceprint ...

Providing Isolation from Distractions

An apparatus includes a first interface for connecting to a personal computer, a second interface for connecting to a communications device, a third interface for connecting to a headset, a fourth interface for connecting to a speaker, and a processor in control of each of the interfaces. The processor is configured to route audio associated with a communications session on one of the personal computer or the communications device to the speaker, and in response to a user putting on the headset, re-route the audio to the headset. 1. An apparatus comprising:a first interface for connecting to a communications device;a second interface for connecting to an audio output device; anda processor in control of each of the interfaces, and configured to: begin analyzing speech from remote participants of the session to produce a voice fingerprint for each remote participant,', "use a speech-to-text process to identify text corresponding to each participants' likely name, and", 'associate the identified text with the voice fingerprint produced for each corresponding remote participant; and, 'upon initiation of a multiple-participant communication session through the communication device,'}when a remote participant speaks during the communication session at a time subsequent to the time their voice fingerprint and likely name was determined, provide an indication to a user of the apparatus of the speaking participant's likely name.2. The apparatus of claim 1 , wherein the indication to the user of the apparatus of the speaking participant's likely name is outputted as text via a user interface in one of: the apparatus claim 1 , the communications device claim 1 , and the audio output device.3. The apparatus of claim 1 , wherein the processor is further configured to:access a calendar event associated with the multiple-participant communication session and determine names of participants listed on the calendar event; anduse the names of the participants listed on the calendar ...

COMBINING PARAMETERS OF MULTIPLE SEARCH QUERIES THAT SHARE A LINE OF INQUIRYSELECTIVELY STORING, WITH MULTIPLE USER ACCOUNTS AND/OR TO A SHARED ASSISTANT DEVICE: SPEECH RECOGNITION BIASING, NLU BIASING, AND/OR OTHER DATA

Some implementations relate to performing speech biasing, NLU biasing, and/or other biasing based on historical assistant interaction(s). It can be determined, for one or more given historical interactions of a given user, whether to affect future biasing for (1) the given user account, (2) additional user account(s), and/or (3) the shared assistant device as a whole. Some implementations disclosed herein additionally and/or alternatively relate to: determining, based on utterance(s) of a given user to a shared assistant device, an association of first data and second data; storing the association as accessible to a given user account of the given user; and determining whether to store the association as also accessible by additional user account(s) and/or the shared assistant device. 1. A method implemented by one or more processors , the method comprising:receiving, via one or more microphones of a shared assistant device that is associated with multiple user accounts, audio data that captures a spoken utterance of a first user;generating, based on processing the audio data, a transcription that corresponds to the spoken utterance captured in the audio data;determining, based on processing the transcription that corresponds to the spoken utterance, at least one assistant action to perform in response to receiving the spoken utterance;classifying the spoken utterance as being spoken by a first user account corresponding to the first user, the first user account being one of the multiple user accounts associated with the shared assistant device; one or more speech biasing parameters that are based on one or more terms of the transcription; and/or', 'wherein storing the one or more biasing parameters in association with the first user account causes future utterances to be processed using the one or more biasing parameters in response to the future utterances being classified as being spoken by the first user account;', 'one or more natural language understanding ...

Responding to emergency calls

According to an aspect, there is provided an apparatus (; FIG. ) for determining an action to be taken in response to an emergency call, the apparatus comprising: a processor (; FIG. ) configured to receive an indication that an emergency call has been initiated; extract, from speech transmitted as part of the emergency call, features indicative of a medical condition or event relating to a subject; obtain medical data relating to the subject; predict, based on the extracted features and the medical data, an acuity level of the subject; determine, based on the acuity level, an action to be taken in respect of the subject; and provide an indication of the determined action for presentation to a recipient. 1. An apparatus for determining an action to be taken in response to an emergency call , the apparatus comprising: receive an indication that an emergency call has been initiated;', 'extract, from speech transmitted as part of the emergency call, features indicative of a medical condition or event relating to a subject;', 'obtain medical data relating to the subject;', 'predict, based on the extracted features and the medical data, an acuity level of the subject;', 'determine, based on the acuity level, an action to be taken in respect of the subject; and', 'provide an indication of the determined action for presentation to a recipient., 'a processor configured to2. An apparatus according to claim 1 , further comprising:a call initiation unit for enabling an emergency call between a caller and a call receiver to be initiated.3. An apparatus according to claim 1 , further comprising:a memory configured to store at least one of: a health record relating to the subject; a predictive model for predicting the acuity level; a predictive model for determining an action to be taken in respect of the subject; and a predictive model for predicting the acuity level and for determining an action to be taken in respect of the subject.4. A computer-implemented method for ...

LOCATION BASED VOICE ASSOCIATION SYSTEM

Systems and methods for providing location based voice recognition include receiving, through a first microphone, an audio signal from a first user that includes an audio command requesting a service that requires user authorization before access to at least a portion of the service is granted. The user authorization is based on voice recognition (e.g., voice authentication and/or voice identification) of the audio signal. The source location of the audio signal is determined and a user location of the first user is determined. If the source location of the audio signal correlates with the user location, voice recognition on the audio signal may be performed. The first user may be authorized to access the service based on the voice recognition performed on the audio signal. 123-. (canceled)24. A voice association system , comprising:a microphone configured to capture an audio signal from an environment surrounding the microphone and convert the audio signal into an electrical signal;a non-transitory memory; and receiving, by the microphone, a first audio signal from a first user of a plurality of users within the environment;', 'determining a first source location of the first audio signal;', 'determining a first user location of the first user and a second user location of a second user;', 'determining that the first user location correlates with the first source location such that the first source location and the first user location are within a predetermined distance of each other;', 'performing, in response to determining that the first user location correlates with the first source location, at least a first security action associated with the first user providing the first audio signal;', 'receiving, by the microphone, a second audio signal;', 'determining a second source location of the second audio signal;', 'determining that the first user is located at the second source location; and', 'performing, in response to determining that the first user is located ...

SPEAKER IDENTIFICATION AND UNSUPERVISED SPEAKER ADAPTATION TECHNIQUES

Systems and processes for generating a speaker profile for use in performing speaker identification for a virtual assistant are provided. One example process can include receiving an audio input including user speech and determining whether a speaker of the user speech is a predetermined user based on a speaker profile for the predetermined user. In response to determining that the speaker of the user speech is the predetermined user, the user speech can be added to the speaker profile and operation of the virtual assistant can be triggered. In response to determining that the speaker of the user speech is not the predetermined user, the user speech can be added to an alternate speaker profile and operation of the virtual assistant may not be triggered. In some examples, contextual information can be used to verify results produced by the speaker identification process. 1. A non-transitory computer-readable storage medium storing one or more programs , the one or more programs comprising instructions for operating a virtual assistant , which when executed by one or more processors of an electronic device , cause the device to:receive current user speech for activating the virtual assistant, wherein the current user speech is associated with current contextual data;select, based on the current contextual data, a first set of stored voiceprints from a plurality of sets of stored voiceprints in a speaker profile of the device, wherein the first set of stored voiceprints is annotated to indicate first contextual data;determine whether a current voiceprint derived from the current user speech matches the first set of stored voiceprints within a predetermined threshold; and add the current voiceprint to the first set of stored voiceprints in the speaker profile;', 'annotate the current voiceprint to indicate the first contextual data; and', 'activate the virtual assistant to process a spoken command received subsequent to the user speech., 'in accordance with a ...

PERSONAL IDENTIFICATION APPARATUS AND PERSONAL IDENTIFICATION METHOD

A personal identification apparatus includes a recording unit that records in advance feature information concerning an activity of at least one of a first person (person A) and a second person (person B or C) when the first person and the second person are together; an information acquiring unit that acquires identification information for identifying the other person; and an identification processing unit that identifies the other person as the second person, based on matching between the identification information and the feature information. 1. A personal identification apparatus that identifies a first person and then identifies another person other than the first person , comprising:a recording unit configured to record in advance feature information concerning an activity performed by at least one of the first person and a second person, when the first person and the second person are together;an information acquiring unit configured to acquire identification information for identifying the other person; andan identification processing unit configured to identify the other person as the second person, based on matching between the identification information and the feature information.2. The personal identification apparatus according to claim 1 , whereinthe identification processing unit identifies the other person without relying on the feature information and, if the other person cannot be identified without relying on the feature information, performs identification based on the matching between the identification information and the feature information.3. The personal identification apparatus according to claim 1 , whereinthe information acquiring unit acquires time information that is a current timing or time span, as the identification information,the feature information includes recorded time information recorded as a timing or time span at or during which the first person performs the activity together with the second person, andthe identification ...

SYSTEM AND METHODS FOR MONITORING VOCAL PARAMETERS

Systems and methods for detection, classification, and diagnosis of vocal anomalies in vocal streams are disclosed. Discussed are a method for generating a biometric voiceprint for analyzing user vocal streams to detect and classify vocal anomalies and a method for notifying the appropriate party, where the notification is based on the diagnosis reported by the system. Manual classification in the event of automatic classification failure is discussed, where the manual classification data can be used as training data to improve the functionality of the classification model. 1. A method for selecting a response based on a cause of a vocal anomaly , the method comprising:establishing, by a device, a biometric voiceprint profile of a user and a threshold for a variation range of the user from the biometric voiceprint profile;monitoring, by the device, a vocal stream of the user;detecting, by the device responsive to monitoring, a vocal anomaly based at least on one or more parameters of the vocal stream exceeding the threshold of the variation range of the user from the one or more parameters of the biometric voiceprint profile;identifying, by the device, responsive to the detection, a cause of the vocal anomaly; andcommunicating, by the device, a notification based at least on the cause of the vocal anomaly.2. The method of claim 1 , further comprising establishing the biometric voiceprint profile using samples of audio data from the user.3. The method of claim 1 , further comprising establishing the biometric voiceprint profile based at least on responses to an assessment to assess one of a health claim 1 , personality or demographic of the user.4. The method of claim 1 , further comprising identifying claim 1 , by the device using one or more classification techniques claim 1 , the vocal anomaly from a plurality of vocal anomalies.5. The method of claim 1 , wherein the one or more parameters of the biometric voiceprint profile comprises one or more of the following: ...

SYSTEM, METHOD, AND RECORDING MEDIUM FOR CONTROLLING DIALOGUE INTERRUPTIONS BY A SPEECH OUTPUT DEVICE

A computer speech output control method, system, and non-transitory computer readable medium, include a computer speech output unit configured to output a computer speech, a human speech monitoring circuit configured to determine whether ambient human conversation including human-to-human speech is occurring, and an interruption determining circuit configured to determine whether to cause the computer speech output unit to output the computer speech based on a status of the human conversation. 1. A computer speech output control system , comprising:a computer speech output unit configured to output a computer speech;a human speech monitoring circuit configured to determine whether ambient human conversation including human-to-human speech is occurring; andan interruption determining circuit configured to determine whether to cause the computer speech output unit to output the computer speech based on a status of the human conversation.2. The system of claim 1 , wherein the interruption determining circuit determines an allowable time for causing the computer speech output unit to output the computer speech based on a priority setting according to an importance of the human conversation and the status of the human conversation.3. The system of claim 1 , wherein the human-to-human speech includes speech directed from a first human to a second human without a need for the computer speech output unit.4. The system of claim 2 , wherein the human speech monitoring circuit is further configured to identify whether a primary user of the system is engaged in the human conversation claim 2 , andwherein an interruption priority setting circuit includes a primary user priority setting in which a specific conditional interruption preference is set up based on the primary user being engaged in the human conversation.5. The system of claim 1 , wherein the human speech monitoring circuit further detects a proximity of humans engaged in the human conversation to the system.6. The ...

Blind Diarization of Recorded Calls With Arbitrary Number of Speakers

In a method of diarization of audio data, audio data is segmented into a plurality of utterances. Each utterance is represented as an utterance model representative of a plurality of feature vectors. The utterance models are clustered. A plurality of speaker models are constructed from the clustered utterance models. A hidden Markov model is constructed of the plurality of speaker models. A sequence of identified speaker models is decoded. 1. A method for automatically transcribing a customer service telephone conversation between an arbitrary number of speakers , the method comprising:receiving data corresponding to the telephone conversation, wherein the received data comprises audio data;separating the audio data into frames;analyzing the frames to identify utterances, wherein each utterance comprises a plurality of frames; identifying homogeneous speaker segments in the audio data, and', 'associating each homogenous speaker segments to a corresponding speaker in the telephone conversation,, 'performing blind diarization of the audio data to differentiate speakers, wherein the blind diarization comprisestagging each homogeneous speaker segment in the telephone conversation with a tag unique for each speaker; comparing the homogeneous speaker segments in the telephone conversation to one or more models retrieved from a database, and', 'based on the comparison, identifying one or more of the speakers; and, "performing speaker diarization to replace one or more of the tags with a speaker's identity, wherein the speaker diarization comprises:"}transcribing the conversation to obtain a text representation of the conversation, wherein each spoken part of the conversation is labeled with either the speaker's identity or the tag associated with the speaker.2. The method according to claim 1 , wherein the identifying homogeneous speaker segments in the audio data comprises using voice activity detection to identify segments of speech separated by segments of non-speech on ...

RECOGNIZING SPEECH IN THE PRESENCE OF ADDITIONAL AUDIO

The technology described in this document can be embodied in a computer-implemented method that includes receiving, at a processing system, a first signal including an output of a speaker device and an additional audio signal. The method also includes determining, by the processing system, based at least in part on a model trained to identify the output of the speaker device, that the additional audio signal corresponds to an utterance of a user. The method further includes initiating a reduction in an audio output level of the speaker device based on determining that the additional audio signal corresponds to the utterance of the user. 1. (canceled)2. A computer-implemented method comprising:receiving, by a first computing device, first audio data that includes an utterance;determining, by the first computing device, that a second computing device is outputting second audio data; andbased on determining that that the second computing device is outputting the second audio data and based on receiving the audio data that includes the utterance, providing, by the first computing device and for output to the second computing device, an instruction to suppress outputting the second audio data.3. The method of claim 2 , comprising:determining, by the first computing device, that the second audio data include speech,wherein providing the instruction to suppress outputting the second audio data is based on determining that the second audio data include speech.4. The method of claim 2 , comprising:determining, by the first computing device, that the first audio data includes speech,wherein providing the instruction to suppress outputting the second audio data is based on determining that the first audio data include speech.5. The method of claim 4 , wherein determining that the first audio data includes speech comprises:providing, as an input to a model that is configured to determine whether received audio data includes speech, the first audio data; andreceiving, from the ...

Association via Voice

A server has a pool data store that stores ambient sound recordings for matching. A match engine finds matches between ambient sound recordings from devices in the pool data store. The matching ambient sound recordings and their respective devices are then analyzed to determine which device is a source device that provides credentials and which device is a target device that receives credentials. The server then obtains or generates credentials associated with the source device and provides the credentials to the target device. The target device accesses content or services of an account using the credentials. 115.-. (canceled)16. A method , comprising:receiving, from a source device associated with a source device account, a source device ambient sound recording;receiving, from a target device, a target device ambient sound recording;matching the source device ambient sound recording and the target device ambient sound recording together based on one or more similarities between the source device ambient sound recording and the target device ambient sound recording; andassociating the target device with the source device account responsive to the matching;wherein the source device ambient sound recording and the target device ambient sound recording is of an utterance spoken by a user.17. The method according to claim 16 , wherein associating the target device with the source device account includes providing credentials to the target device.18. The method according to claim 16 , further comprising:providing the source device ambient sound recording for matching responsive to determining that the source device ambient sound recording includes a log-in utterance; andproviding the target device ambient sound recording for matching responsive to determining that the target device ambient sound recording includes the log-in utterance.19. The method according to claim 16 , further comprising:obtaining target device signals from the target device; andwherein matching the ...

Method for Controlling Wearable Device, Wearable Device, and Storage Medium

A method for controlling a wearable device includes: acquiring voice information collected by an acoustoelectric element and vibration information collected by a vibration sensor, in which the acoustoelectric element and the vibration sensor are included in the wearable device; determining a voice command based on the voice information; determining identity information of the voice command based on the voice information and the vibration information; and executing or ignoring the voice command based on the identity information. 1. A method for controlling a wearable device , wherein , the wearable device comprises an acoustoelectric element and a vibration sensor , the method comprising:acquiring voice information collected by the acoustoelectric element and vibration information collected by the vibration sensor;determining a voice command based on the voice information;determining identity information of the voice command based on the voice information and the vibration information; andexecuting or ignoring the voice command based on the identity information.2. The method of claim 1 , wherein claim 1 , determining the identity information of the voice command comprises:determining a time difference between the voice information and the vibration information; anddetermining the identity information based on the time difference.3. The method of claim 2 , wherein claim 2 , the identity information comprises a wearer and a non-wearer claim 2 , and the time difference comprises a start time difference claim 2 , and determining the identity information of the voice command comprises:determining the start time difference based on a start moment of the voice information and a start moment of the vibration information;in response to the start time difference being less than or equal to a preset time threshold, determining that the identity information of the voice command is the wearer; andin response to the start time difference being greater than the preset time ...

Systems and methods for filtering unwanted sounds from a conference call using voice synthesis

To filter unwanted sounds from a conference call, a first voice signal is captured by a first device during a conference call and converted into corresponding text, which is then analyzed to determine that a first portion of the text was spoken by a first user and a second portion of the text was spoken by a second user. If the first user is relevant to the conference call while the second user is not, the first voice signal is prevented from being transmitted into the conference call, the first portion of text is converted into a second voice signal using a voice profile of the first user to synthesize the voice of the first user, and the second voice signal is then transmitted into the conference call. The second portion of text is not converted into a voice signal, as the second user is determined not to be relevant.

METHODS AND SYSTEMS FOR SOUND SOURCE LOCATING

A method and system for locating a sound source are provide. The method may include detecting a sound signal of a sound by each of two audio sensors. The method may also include converting the sound signals detected by the two audio sensors from a time domain to a frequency domain. The method may further include determining a high frequency ratio of each of the sound signals in the frequency domain. The method may further include determining a direction of the sound source based on the high frequency ratios. 1. A system comprisinga storage device storing a set of instructions; and detecting a sound signal of a sound source;', 'determining a position of the sound source based on a high frequency ratio of the sound signal in a frequency domain, wherein the high frequency ratio relates to a percentage of a high frequency component in the sound signal;', 'determining, based on the position of the sound source, a control signal; and', 'causing a device to operate according to the control signal., 'a processor in communication with the storage device, wherein when executing the set of instructions, the processor is configured to cause the system to perform operations including2. The system of claim 1 , wherein the device is an audio sensor claim 1 , the causing the device to operate according to the control signal comprising:causing the audio sensor to obtain a sound signal according to the control signal.3. The system of claim 1 , wherein the processor is further configured to cause the system to perform the operations including:determining reference information relating to the sound source, the reference information including at least one of wind speed or wind direction; anddetermining three-dimensional coordinates of the position of the sound source based on the sound signal and the reference information.4. The system of claim 1 , wherein the processor is further configured to cause the system to perform the operations including:determining reference information ...

METHOD AND APPARATUS FOR VOICE RECORDING AND PLAYBACK

Methods and apparatuses are provided for controlling an electronic device that includes a plurality of microphones configured to receive voice input, a storage unit configured to store a sound recording file, and a display unit configured to visually display speaker areas of individual speakers when recording a sound or playing a sound recording file. The electronic device also includes a control unit configured to provide a user interface relating a speaker direction to a speaker by identifying the speaker direction while recording the sound or performing playback of the sound recording file, and to update at least one of speaker information, direction information of a speaker, and distance information of the speaker through the user interface. 1. A method for operating an electronic device , the method comprising the steps of:identifying a speaker from an acoustic signal;determining a direction from the electronic device to the speaker;providing a user interface for the acoustic signal based on the direction from the electronic device to the speaker; andupdating the user interface.2. The method of claim 1 , wherein the updating the user interface comprises:displaying speaker information and direction information in a visual form when sound recording is performed on the acoustic signal; andstoring a sound recording file with distinguished individual speakers, when the sound recording of the acoustic signal is terminated.3. The method of claim 2 , wherein updating the user interface comprises:identifying the speaker based on the acoustic signal; anddisplaying the speaker information based on the identification of the speaker.4. The method of claim 2 , wherein storing the sound recording file comprises storing a voice of the speaker claim 2 , direction information of the speaker claim 2 , and distance information of the speaker.5. The method of claim 1 , wherein identifying the direction from the electronic device to the speaker comprises:identifying the direction ...

METHODS AND VEHICLES FOR CAPTURING EMOTION OF A HUMAN DRIVER AND MODERATING VEHICLE RESPONSE

Methods and systems for determining an emotion of a human driver of a vehicle and using the emotion for generating a vehicle response, is provided. One example method includes capturing, by a camera of the vehicle, a face of the human driver. The capturing is configured to capture a plurality of images over a period of time, and the plurality of images are analyzed to identify a facial expression and changes in the facial expression of the human driver over the period of time. The method further includes capturing, by a microphone of the vehicle, voice input of the human driver. The voice input is captured over the period of time. The voice input is analyzed to identify a voice profile and changes in the voice profile of the human driver over the period of time. The method processes, by a processor of the vehicle, a combination of the facial expression and the voice profile captured during the period of time to predict the emotion of the human driver. The method generates the vehicle response that is responsive to the emotion of the human driver. The vehicle response is configured to make at least one adjustment to a setting of the vehicle. The adjustment is selected based on the emotion of the human driver. The vehicle response can be used to make the driver more calm and/or assist in reducing distracted driving. The prediction of the emotion may be additionally increased by capturing and analyzing touch and/or gesture characteristic of the human driver when interfacing with a graphical user interface or surfaces of the vehicle or systems of the vehicle. 1. A method for determining an emotion of a human driver of a vehicle and using the emotion for generating a vehicle response , comprising ,capturing, by a camera of the vehicle, a face of the human driver, the capturing is configured to capture a plurality of images over a period of time, the plurality of images being analyzed to identify a facial expression and changes in the facial expression of the human driver ...

PERSONALIZATION OF EXPERIENCES WITH DIGITAL ASSISTANTS IN COMMUNAL SETTINGS THROUGH VOICE AND QUERY PROCESSING

In non-limiting examples of the present disclosure, systems, methods and devices for providing personalized experiences to a computing device based on user input such as voice, text and gesture input are provided. Acoustic patterns associated with voice input, speech patterns, language patterns and natural language processing may be used to identify a specific user providing input from a plurality of users, identify user background characteristics and traits for the specific user, and topically categorize user input in a tiered hierarchical index. Topically categorized user input may be supplemented with user data and world knowledge and personalized responses and feedback for an identified specific user may be provided reactively and proactively. 1. A method for providing personalized experience from voice analysis , comprising:receiving a voice input from a first user;analyzing acoustic patterns of the voice input;determining, based on the acoustic analysis, the identity of the first user;extracting, from the voice input, at least one signal pertaining to a background characteristic of the first user and at least one signal pertaining to a digital characteristic associated with the first user;assigning values to the at least one extracted signal pertaining to the background characteristic of the first user and the at least one extracted signal pertaining to the digital characteristic associated with the first user;categorizing the voice input into one or more topical categories using the assigned values and natural language speech processing; andproviding a personalized response related to the voice input.2. The method of claim 1 , wherein determining the identity of the first user further comprises matching the voice input to an acoustic profile claim 1 , the acoustic profile comprising: a gender acoustic pattern claim 1 , an age group acoustic pattern claim 1 , and an accent acoustic pattern claim 1 , wherein the gender acoustic pattern claim 1 , the age group ...

FRIEND ADDITION METHOD, DEVICE AND MEDIUM

A friend addition method, device and medium are provided. The method includes: when a voiceprint-based friend addition request is received, target voice information is acquired; user information of a user to be added is determined according to the target voice information; and the user to be added is added as a friend according to the user information. 1. A friend addition method , applied to a client , the method comprising:acquiring target voice information when a voiceprint-based friend addition request is received;determining user information of a user to be added according to the target voice information; andadding the user to be added as a friend according to the user information.2. The method according to claim 1 , after acquiring the target voice information claim 1 , the method further comprising:identifying voice content in the target voice information;judging whether the voice content matches with a pre-generated voiceprint identification statement or not; andnot executing the friend addition operation when the voice content does not match with the pre-generated voiceprint identification statement.3. The method according to claim 1 , wherein determining the user information of the user to be added according to the target voice information comprises:extracting voiceprint information in the target voice information;sending the voiceprint information to a network side to enable the network side to search for user information corresponding to the voiceprint information according to a pre-stored relationship between voiceprint information and user information; andreceiving the user information returned by the network side as the user information of the user to be added.4. The method according to claim 3 , after sending the voiceprint information to the network side claim 3 , the method further comprising:receiving and outputting prompting information returned by the network side, the prompting information indicating that the network side does not store the ...

ELECTRONIC DEVICE AND OPERATION METHOD FOR PERFORMING SPEECH RECOGNITION

An electronic device for performing speech recognition and a method therefor are provided. The method includes detecting a first text, which is preset for performing speaker recognition, by performing speech recognition on a first speech signal, performing speaker recognition on a second speech signal acquired after the first speech signal, based on the first text being detected, and executing a voice command obtained from the second speech signal, based on a result of performing the speaker recognition on the second speech signal indicating that a speaker of the second speech signal corresponds to a first speaker who registered the first text. 1. A method of performing speech recognition by an electronic device , the method comprising:detecting a first text, which is preset for performing speaker recognition, by performing speech recognition on a first speech signal;performing speaker recognition on a second speech signal acquired after the first speech signal, based on the first text being detected; andexecuting a voice command obtained from the second speech signal, based on a result of performing the speaker recognition on the second speech signal indicating that a speaker of the second speech signal corresponds to a first speaker who registered the first text.2. The method of claim 1 , wherein the performing of the speaker recognition on the second speech signal comprises:acquiring, based on the first speech signal, a speech signal interval in which the first text is uttered;performing the speaker recognition on the speech signal interval; andperforming the speaker recognition on the second speech signal, based on a result of performing the speaker recognition on the speech signal interval indicating that a speaker of the speech signal interval corresponds to the first speaker.3. The method of claim 2 ,wherein the voice command obtained from the second speech signal is executed based on whether a degree of correspondence between the speaker of the second speech ...

METHODS AND VEHICLES FOR PROCESSING VOICE INPUT AND USE OF TONE/MOOD IN VOICE INPUT TO SELECT VEHICLE RESPONSE

Methods, systems and cloud processing are provided for coordinating and processing user input provided to vehicles during use. One example is for processing voice inputs at a vehicle to identify a mood of a user and then modifying or customizing the vehicle response based on the detected mood, physical characteristic and/or physiological characteristic of the user. One example includes a vehicle having an on-board computer for processing voice input. The vehicle having a microphone interfaced with the on-board computer and memory for storing a sample of audio data received from the microphone. The audio data is a voice input directed to the vehicle. A processor of the on-board computer is configured to process the sample of audio data to identify markers in frequency and/or magnitude. The markers are used to define an audio signature for the voice input, and the audio signature is used to identify a voice profile. The voice profile is used to identify a vehicle response for the voice input, and the voice profile is associated with tone of voice used in the voice input. The vehicle response acts to direct a vehicle system function to take an action based on the voice input and the vehicle response is adjusted based on the tone of voice. The tones of voice are associated to inferred moods of the user which include one or more of a normal mood, a frustrated mood, an agitated mood, an upset mood, a hurried mood, an urgency mood, a rushed mood, a stressed mood, a calm mood, a passive mood, a sleepy mood, a happy mood, or an excited mood, or combinations of two or more thereof. The action to be taken is based on the voice input and is one of a command to input a setting of the vehicle, a command requesting information, a request to access data, a request to communicate, or a combination thereof. 1. A method for processing voice inputs at a vehicle , comprising ,sending, to a server, data from the vehicle, the vehicle including an on-board computer for processing ...

SPEAKER VERIFICATION METHODS AND APPARATUS

Techniques for automatically identifying a speaker in a conversation as a known person based on processing of audio of the speaker's voice to extract characteristics of that voice and on an automated comparison of those characteristics to known characteristics of the known person's voice. A speaker segmentation process may be performed on audio of the conversation to produce, for each speaker in the conversation, a segment that includes the audio of that speaker. Audio of each of the segments may then be processed to extract characteristics of that speaker's voice. The characteristics derived from each segment (and thus for multiple speakers) may then be compared to characteristics of the known person's voice to determine whether the speaker for that segment is the known person. For each segment, a degree of match between the voice characteristics of the speaker and the voice characteristics of the known person may be calculated. 1. A method of evaluating whether a first speaker in a conversation is a user whose identity has been asserted by analyzing audio of the conversation , wherein the conversation involves a second speaker whose identity is known , and wherein at least a portion of the audio of the conversation has been decomposed into a first segment and a second segment , each of the first segment and the second segment being composed substantially of audio of a single speaker speaking in the conversation , the method comprising:comparing the first segment to a first voiceprint of the user to determine a first likelihood that the first segment corresponds to the user;comparing the first segment to a second voiceprint of the second speaker to determine a second likelihood that the first segment corresponds to the second speaker;comparing the second segment to the first voiceprint of the user to determine a third likelihood that the second segment corresponds to the user;comparing the second segment to the second voiceprint of the second speaker to determine a ...

METHODS AND SYSTEMS FOR INTELLIGENT CONTENT CONTROLS

Provided are methods and systems for intelligent content controls. A command may be received during presentation of content. The command may be time-driven, context-driven, or a combination of both. An end boundary may be determined based on a duration of time and/or one or more words of the command. Presentation of the content may be terminated at a nearest content transition with respect to the end boundary. 1. A method comprising:receiving a command associated with enforcement of content controls during presentation of a scene of content;determining, based on a portion of the command relating to metadata associated with the scene of the content and a timestamp, an end boundary; andcausing presentation of the content to be terminated at the end boundary.2. The method of claim 1 , wherein the command comprises a voice signature.3. The method of claim 2 , further comprising determining claim 2 , based on the voice signature claim 2 , that the command is authorized.4. The method of claim 1 , wherein the portion of the command comprises one or more keywords relating to the metadata associated with the scene of the content and the timestamp.5. The method of claim 1 , wherein the content is presented at a user device claim 1 , and wherein causing presentation of the content to be terminated at the end boundary comprises one or more of:causing the user device to power off at the timestamp;causing the user device to disregard a further command received at the user device at or following the timestamp; orcausing the user device to present a screensaver at the timestamp.6. The method of claim 1 , further comprising determining claim 1 , based on a content transition occurring during presentation of the content nearest the timestamp claim 1 , an adjusted end boundary claim 1 , wherein presentation of the content is caused claim 1 , based on the adjusted end boundary claim 1 , to be terminated at the content transition.7. The method of claim 1 , further comprising:determining ...

ELECTRONIC DEVICE WITH A FUNCTION OF SMART VOICE SERVICE AND METHOD OF ADJUSTING OUTPUT SOUND

An electronic device with a function of smart voice service is disclosed. The electronic device is capable of identifying a user who is using the function of smart voice service and of adjusting the frequency of output sound to answer according to the hearing state of the user. 1. An electronic device with a function of smart voice service , comprising:a speaker;a memory;an input device, used for acquiring a recognition feature data of a user, wherein the input device includes a microphone for receiving a voice message made by the user; and a file creation module, used for creating an interactor database and storing the interactor database in the memory, wherein the interactor database includes an identification data and a hearing parameter data of a plurality of interactors;', 'an identity recognition module, used for analyzing the recognition feature data so as to obtain an identity verification data, and for comparing the identity verification data with the identification data of the plurality of interactors in order to obtain the corresponding hearing parameter data;', 'an answer message acquisition module, used for acquiring a corresponding original answer voice message appropriate for answering the voice message; and', 'a sound adjustment module, used for adjusting the original answer voice message according to the hearing parameter data, so as to generate an adjusted answer voice message for the speaker to output the adjusted answer voice message., 'a processing unit, electrically connected to the speaker, the memory and the input device, the processing unit comprising2. The electronic device as claimed in claim 1 , wherein the electronic device is connected to a server system claim 1 , such that the answer message acquisition module first transmits the voice message to the server system claim 1 , and then the server system obtains the original answer voice message claim 1 , wherein the original answer voice message is obtained by the server system according ...

Dynamically resolving names and acronyms

At least one target in a speech of a first speaker during an electronic conference is identified. A closest vector between the identified target and a group of possible matches for the target is determined. A most similar match for the identified target is determined based on a current usage context for the identified target, a history of stored information associated with the first speaker and the identified target, and the determined closest vector. The most similar match to a set of participants of the electronic conference is displayed.

User authentication using prompted text

Methods, computing systems and computer program products implement embodiments of the present invention that include defining a verification string including a sequence of verification characters and a delimiter character between each sequential pair of the verification characters, the delimiter character being different from the verification characters. The verification string to a user, and upon receiving, from the user, a series of verification vocal inputs in response to presenting the verification string, a set of verification features from each of the verification vocal inputs are computed so as to generate sets of verification features. A one-to-one correspondence is established between each of the verification vocal inputs and each of the verification characters, and the user is authenticated based on the verification vocal inputs and their corresponding sets of verification features. 1. A method , comprising:defining a verification string comprising a sequence of verification characters and a delimiter character between each sequential pair of the verification characters, the delimiter character being different from the verification characters;presenting the verification string to a user;receiving, from the user, a series of verification vocal inputs in response to presenting the verification string;computing a set of verification features from each of the verification vocal inputs so as to generate sets of verification features;establishing a one-to-one correspondence between each of the verification vocal inputs and each of the verification characters; andauthenticating the user based on the verification vocal inputs and their corresponding sets of verification features.2. The method according to claim 1 , and further comprising prior to defining the verification string:defining an enrollment string comprising a sequence of enrollment characters and the delimiter character between each sequential pair of the enrollment characters, the delimiter character ...

Voiceprint registration method, server and storage medium

Embodiments of the present disclosure provide a voiceprint registration method, a server and a storage medium. The method may include: acquiring present speech information collected by a smart device; extracting a present voiceprint feature of the present speech information; determining whether the present voiceprint feature is a voiceprint feature associated with the smart device; and determining the present voiceprint feature as a user identification associated with the smart device to determine the present voiceprint feature as the voiceprint feature associated with the smart device, in response to determining that the present voiceprint feature is not the voiceprint feature associated with the smart device.

Apparatuses and Methods for Audio Classifying and Processing

Apparatus and methods for audio classifying and processing are disclosed. In one embodiment, an audio processing apparatus includes an audio classifier for classifying an audio signal into at least one audio type in real time; an audio improving device for improving experience of audience; and an adjusting unit for adjusting at least one parameter of the audio improving device in a continuous manner based on the confidence value of the at least one audio type. 1. An audio processing apparatus comprising:an audio classifier for classifying an audio signal into at least one audio type in real time;an audio improving device for improving experience of audience; andan adjusting unit for adjusting at least one parameter of the audio improving device in a continuous manner based on the confidence value of the at least one audio type, wherein the at least one audio type comprises at least one of content types of short-term music, speech, background sound and noise, and/or at least one of context types of long-term music, movie-like media, game and VoIP.2. The audio processing apparatus according to claim 1 , wherein the at least one audio type comprises context type of VoIP or non-VoIP and the short-term music comprises music without dominant sources or music with dominant sources.3. The audio processing apparatus according to claim 2 , wherein the short-term music comprises at least one genre-based cluster or at least one instrument-based cluster or at least one music cluster classified based on rhythm claim 2 , tempo claim 2 , timbre of music and/or any other musical attributes.4. The audio processing apparatus according to claim 1 , where the audio improving device comprises at least one selected from a dialog enhancer claim 1 , a surround virtualizer claim 1 , a volume leveler and an equalizer.5. The audio processing apparatus according to claim 2 , wherein the audio improving device comprises at least one selected from a dialog enhancer claim 2 , a surround ...

SYSTEM AND METHOD FOR DIARIZATION BASED DIALOGUE ANALYSIS

A preferred embodiment of the invention relates to a dialogue analysis system that can analyze speech of a user communicating with other participants in a dialogue. The user can be a lead speaker of the dialogue. The dialogue analysis system can receive voice signals of the user and the other participants from their respective communication devices. Subsequently, the dialogue analysis system can identify speech of a user in order to differentiate that speech from speeches of other participants. The dialogue analysis system can analyze the speech of the user as well as collective speeches of the other participants. Based on the analysis, the dialogue analysis system can generate a customized report for the user. The dialogue analysis system can deliver the customized report for the user to a computing device. 1. A system for dialogue analysis comprising:a network-connected dialogue analysis computer comprising at least a memory and a processor and further comprising programmable instructions stored in the memory and operating on the processor, the instructions adapted to a system for analyzing recorded dialogue data captured data from an audio source comprising:a dialogue processing module;a parsed dialogue module;a question identification and tagging module;a communication reporting and feedback module;wherein the dialog processing module captures, stores, and processes the recorded dialogue data;wherein the parsed dialogue module identifies a plurality of speakers, and, at least, audio characteristics data within the recorded dialogue data;wherein the question identification and tagging module identifies one or more question statements within the recorded dialogue data and evaluates the one or more question statements, based at least in part on audio characteristics data to produce an evaluation;wherein communication reporting and feedback module provides feedback to a computing device, the feedback based on the evaluation.2. The system of claim 1 , wherein the ...