Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 5717. Отображено 100.
15-03-2012 дата публикации

System for extraction of reverberant content of an audio signal

Номер: US20120063608A1
Автор: Gilbert Arthur Joseph Soulodre
Принадлежит: Harman International Industries Inc

A reverberant characteristic of an acoustic space is superimposed on an audio signal that is received by an apparatus. The apparatus decomposes the audio signal into an estimated original dry signal component and an estimated reverberant characteristic of the acoustic space. Estimation of the original dry signal component and the reverberant characteristic of the acoustic space is based on determination of an estimated impulse response of the acoustic space from the received audio signal. Once the audio signal is decomposed, the estimated original dry signal component and the estimated reverberant characteristic of the acoustic space may be independently modified by the apparatus. The modified or unmodified estimated original dry signal component and estimated reverberant characteristic of the acoustic space may be combined by the apparatus to produce one or more adjusted frequency spectra.

Подробнее
Номер записи: 1
19-07-2012 дата публикации

Device and method for controlling damping of residual echo

Номер: US20120183133A1
Автор: Christian Schuldt, Fredrick Lindström, Ingvar Claesson
Принадлежит: Limes Audio AB

The present invention relates to a device, such as a communication device, comprising an adaptive foreground filter configured to calculate a first echo estimation signal based on a first input signal, and an adaptive background filter being more rapidly adapting than the foreground filter and configured to calculate a second echo estimation signal based on said first input signal. Embodiments of the device further comprise damping control means for controlling damping of an echo-cancelled output signal. The device in various embodiments includes that the damping control means is configured to calculate a maximum echo estimation signal using both the first and the second echo estimation signals, and control the damping of the echo-cancelled output signal based on said maximum echo estimation signal and/or a signal derived from said maximum echo estimation signal.

Подробнее
Номер записи: 2
15-11-2012 дата публикации

Method and apparatus for processing multi-channel de-correlation for cancelling multi-channel acoustic echo

Номер: US20120288100A1
Автор: Nam-gook CHO
Принадлежит: SAMSUNG ELECTRONICS CO LTD

Provided are a method and apparatus for multi-channel de-correlation processing for cancelling a multi-channel acoustic echo. The method includes: dividing an input multi-channel audio signal into units of frames to form multi-channel audio signals in units of frames; analyzing eigen values and eigen vectors related to the multi-channel audio signals by using the multi-channel audio signals in units of frames every time contents are modified; and separating the multi-channel audio signals in units of frames into a plurality of signal component spaces by using the analyzed eigen values and eigen vectors.

Подробнее
Номер записи: 3
22-11-2012 дата публикации

Method and apparatus for reducing noise pumping due to noise suppression and echo control interaction

Номер: US20120294453A1
Автор: Andrew John Macdonald, Björn Völcker, Jan Skoglund
Принадлежит: Andrew John Macdonald, Jan Skoglund, Volcker Bjoern

An input signal is processed through noise suppression (NS) and echo control (EC) via a multipath model that reduces noise pumping effects while maintaining EC performance. A copy of a “noisy” input signal is sent to an EC component before the noisy signal is sent to a NS component, which processes the signal first, when there is a consistent noise level for estimation. The copy of the pre-processing noisy signal is sent to the EC component along with a “clean” or “noise-suppressed” signal output from the NS component. The EC component analyzes the noisy signal as if the EC was the first component in the signal chain to determine what actions to take. The EC component then applies these actions to the clean signal received from the NS component.

Подробнее
Номер записи: 4
14-02-2013 дата публикации

Methods and apparatuses for echo cancelation with beamforming microphone arrays

Номер: US20130039504A1
Автор: Ashutosh Pandey, Darrin T. Thurston, David K. Lambert, Tracy A. Bathurst
Принадлежит: ClearOne Communications Inc

Embodiments include methods and apparatuses for sensing acoustic waves for a conferencing application. A conferencing apparatus includes a plurality of microphones oriented to cover a corresponding plurality of direction vectors and to develop a corresponding plurality of microphone signals. A processor is operably coupled to the plurality of microphones. The processor is configured to perform a beamforming operation to combine the plurality of microphone signals to a plurality of combined signals that is greater in number than one and less in number than the plurality of microphone signals. The processor is also configured perform an acoustic echo cancelation operation on the plurality of combined signals to generate a plurality of combined echo-canceled signals and select one of the plurality of combined echo-canceled signals for transmission.

Подробнее
Номер записи: 5
14-03-2013 дата публикации

Echo Cancelling-Codec

Номер: US20130066638A1
Автор: Phillip Alan Hetherington, Shree Paranjpe, Steven George MASON
Принадлежит: QNX Software Systems Ltd

Echo-cancellation is utilized in terminal devices such as speakerphones to compensate for acoustic echoes and interaction of the audio signal with the surrounding environment. An echo-cancelling codec incorporates encoding, decoding and acoustic echo-cancellation in a single device, enabling processing to be utilized that reduces processing and memory resources. The configuration enables processing information to also be shared between encoding, decoding and acoustic echo-cancellation functions to optimize operational characteristics. The acoustic echo cancelling codec interfaces between the amplitude signal domain, speaker and microphone, and an encoded data domain, a data interface, reducing component requirements required to provide echo-cancellation and coding functions.

Подробнее
Номер записи: 6
11-04-2013 дата публикации

Mobile device context information using speech detection

Номер: US20130090926A1
Автор: Leonard Henry Grokop, Shankar Sadasivam
Принадлежит: Qualcomm Inc

Systems and methods for speech detection in association with a mobile device are described herein. A method described herein for identifying presence of speech associated with a mobile device includes obtaining a plurality of audio samples from the mobile device while the mobile device operates in a mode distinct from a voice call operating mode, generating spectrogram data from the plurality of audio samples, and determining whether the plurality of audio samples include information indicative of speech by classifying the spectrogram data.

Подробнее
Номер записи: 7
13-06-2013 дата публикации

Apparatus, System, and Method For Distinguishing Voice in a Communication Stream

Номер: US20130151248A1
Автор: Forrest Baker, IV
Принадлежит: Noguar LC

An apparatus for distinguishing a voice is described. In one embodiment, the apparatus includes a server with a communication interface, a frame generator, and a sound analyzer. The communication interface processes an incoming communication stream with an echo canceller to cancel echo in the communication stream. The frame generator operates on a processor and generates a plurality of frames from the communication stream. Each of the plurality of frames contains data for a period of time from the communication stream. The frame generator also assigns a frame value to each of the plurality of frames. The sound analyzer determines a status of the communication stream by analyzing the frame values of the plurality of frames.

Подробнее
Номер записи: 8
18-07-2013 дата публикации

Echo removing apparatus, echo removing method, program and recording medium

Номер: US20130185064A1
Автор: Mitsuhiro Suzuki
Принадлежит: Sony Corp

To be provided is an echo removing apparatus including a transmission path estimate update processing unit, and an output selection unit. A fixed section of the transmission path estimate is updated based on an error from an echo estimate determined using all of the fixed section, the holding section, and the update section. These sections are updated depending on whether an estimate obtained by adding the fixed section and the holding section is better than an estimate of the fixed section alone in every fixed period. Only when the estimate is better, the holding section is added to the fixed section cumulatively, and the update section is substituted into the holding section. Depending on whether an estimate is better, an error from the eco estimate determined using all these sections or the fixed section alone is selected as an output.

Подробнее
Номер записи: 9
31-10-2013 дата публикации

Reduced-delay subband signal processing system and method

Номер: US20130287226A1
Автор: Yair Kerner
Принадлежит: Conexant Systems LLC

A method for signal processing, receiving a time domain signal having a sample-rate Fs and generating N time domain signal bands, each having a bandwidth equal to Fs/N. Receiving the N signal bands and transforming a first time domain signal band to a frequency domain at a first resolution and a second time domain signal band to the frequency domain at a second resolution, where the first resolution may be different from the second resolution. Determining one or more first filter coefficients using the frequency domain components from the first signal band and one or more second filter coefficients using the frequency domain components from the second signal band. Transforming the first and second filter coefficients from the frequency domain to a time domain. Applying the first and second time domain filter coefficients to the first and second time domain signals, respectively.

Подробнее
Номер записи: 10
06-01-2022 дата публикации

AUTOMATED TRANSCRIPT GENERATION FROM MULTI-CHANNEL AUDIO

Номер: US20220005492A1
Автор: DaSilva David Joseph, Donofrio Anthony, JR. James Andrew, Kaplan Jonathan Mordecai, Maraska
Принадлежит:

Systems and methods are described for generating a transcript of a legal proceeding or other multi-speaker conversation or performance in real time or near-real time using multi-channel audio capture. Different speakers or participants in a conversation may each be assigned a separate microphone that is placed in proximity to the given speaker, where each audio channel includes audio captured by a different microphone. Filters may be applied to isolate each channel to include speech utterances of a different speaker, and these filtered channels of audio data may then be processed in parallel to generate speech-to-text results that are interleaved to form a generated transcript. 1a plurality of microphones;audio mixer hardware configured to process a plurality of audio channels, wherein each of the plurality of microphones corresponds to a different channel of the plurality of audio channels; and receiving speaker identification information for each of the plurality of audio channels, wherein the speaker identification information for each individual audio channel identifies a person assigned to the individual audio channel and vocal characteristic information of the person, wherein the person assigned to the individual audio channel is physically located closer to a microphone assigned to the individual audio channel than to any other microphone of the plurality of microphones;', 'selecting a speech model to be used with respect to audio data for each of two or more of the plurality of audio channels, wherein a first speech model selected for a first audio channel is based at least in part on vocal characteristic information of a first person assigned to the first audio channel;', 'receiving at least a portion of multi-channel streaming audio from the audio mixer hardware, wherein the multi-channel streaming audio comprises audio signals captured from each of the plurality of microphones on a different channel of the plurality of audio channels;', 'applying one or ...

Подробнее
Номер записи: 11
07-01-2016 дата публикации

NONLINEAR ACOUSTIC ECHO SIGNAL SUPPRESSION SYSTEM AND METHOD USING VOLTERRA FILTER

Номер: US20160005419A1
Автор: CHANG Joon Hyuk, PARK Ji Hwan
Принадлежит:

A nonlinear acoustic echo signal suppression system and method using a Volterra filter is disclosed. The nonlinear acoustic echo signal suppression system includes an acoustic echo signal estimator configured to estimate a nonlinear acoustic echo signal by using a Volterra filter in a frequency filter, and a near-end talker speech signal generator configured to generate a near-end talker speech signal, in which the nonlinear acoustic echo signal is suppressed, by using a gain function based on a statistical model. 1. A nonlinear acoustic echo signal suppression system comprising:an acoustic echo signal estimator configured to estimate a nonlinear acoustic echo signal by using a Volterra filter in a frequency filter; anda near-end talker speech signal generator configured to generate a near-end talker speech signal, in which the nonlinear acoustic echo signal is suppressed, by using a gain function based on a statistical model.2. The nonlinear acoustic echo signal suppression system according to claim 1 , wherein the acoustic echo signal estimator is configured to estimate a filter factor of the Volterra filter by using a multi-tap least square estimator claim 1 , and estimate the nonlinear acoustic echo signal by using the filter factor of the Volterra filter.3. The nonlinear acoustic echo signal suppression system according to claim 1 , wherein the near-end talker speech signal generator is configured to estimate a prior near-end talker speech presence probability ratio claim 1 , which is variable claim 1 , from a data-driven algorithm claim 1 , and generate the near-end talker speech signal from the estimated prior near-end talker speech presence probability ratio and the gain function.4. The nonlinear acoustic echo signal suppression system according to claim 3 , wherein the prior near-end speech presence probability ratio is variable according to the near-end talker speech signal claim 3 , and applied to near-end speech absence probability based on a complex ...

Подробнее
Номер записи: 12
07-01-2021 дата публикации

Detecting Self-Generated Wake Expressions

Номер: US20210005197A1
Автор: Hilmes Philip Ryan, Pogue Michael Alan
Принадлежит:

A speech-based audio device may be configured to detect a user-uttered wake expression. For example, the audio device may generate a parameter indicating whether output audio is currently being produced by an audio speaker, whether the output audio contains speech, whether the output audio contains a predefined expression, loudness of the output audio, loudness of input audio, and/or an echo characteristic. Based on the parameter, the audio device may determine whether an occurrence of the predefined expression in the input audio is a result of an utterance of the predefined expression by a user. 120-. (canceled)21. A device comprising:a first microphone;a second microphone;one or more processors; and generate, at a first time and using the first microphone, first audio data corresponding to sound;', 'generate, at a second time and using the second microphone, second audio data corresponding to the sound;', 'determine a difference between the first time and the second time;', 'generate, based at least in part on the difference, beamforming data using the first audio data and the second audio data; and', 'perform speech recognition on the beamforming data., 'one or more non-transitory storage media storing computer-executable instructions that, when executed by the one or more processors, cause the system to22. The device of claim 21 , wherein generating the beamforming data comprises generating directional audio data that emphasizes a first portion of at least one of the first audio data or the second audio data with respect to a second portion of at least one of the first audio data or the second audio data.23. The device of claim 21 , wherein the first microphone and the second microphone are directed upward from a top portion of the device.24. The device of claim 21 , wherein the first microphone and the second microphone comprise at least a portion of a circular arrangement of microphones.25. The device of claim 21 , wherein generating the beamforming data ...

Подробнее
Номер записи: 13
07-01-2021 дата публикации

Detecting Self-Generated Wake Expressions

Номер: US20210005198A1
Автор: Hilmes Philip Ryan, Pogue Michael Alan
Принадлежит:

A speech-based audio device may be configured to detect a user-uttered wake expression. For example, the audio device may generate a parameter indicating whether output audio is currently being produced by an audio speaker, whether the output audio contains speech, whether the output audio contains a predefined expression, loudness of the output audio, loudness of input audio, and/or an echo characteristic. Based on the parameter, the audio device may determine whether an occurrence of the predefined expression in the input audio is a result of an utterance of the predefined expression by a user. 120-. (canceled)21. A system comprising:one or more microphones;one or more audio speakers;one or more processors; and generate, using the one or more microphones, first audio data;', 'determine one or more parameters associated with the first audio data;', 'analyze, using the one or more parameters, the first audio data to generate text data corresponding to the first audio data; and', 'cause, using the one or more audio speakers and based at least partly on the text data, output of second audio data., 'non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the system to22. The system of claim 21 , wherein a first parameter of the one or more parameters corresponds to an audio input characteristic and a second parameter of the one or more parameters corresponds to a device operation characteristic.23. The system of wherein the audio input characteristic comprises an echo characteristic associated with the first audio data or a loudness characteristic associated with the first audio data.24. The system of claim 22 , wherein the device operation characteristic comprises a presence of the one or more audio speakers claim 22 , a loudness characteristic of sound generated by the one or more audio speaker claim 22 , or an amount of echo reduction performed by the one or more processors.25. The system of claim 21 , ...

Подробнее
Номер записи: 14
04-01-2018 дата публикации

DEVICE INCLUDING SPEECH RECOGNITION FUNCTION AND METHOD OF RECOGNIZING SPEECH

Номер: US20180005627A1
Автор: ABE Kazutaka, MIYASAKA Shuji
Принадлежит:

A device including a speech recognition function which recognizes speech from a user, includes: a loudspeaker which outputs speech to a space; a microphone which collects speech in the space; a first speech recognition unit which recognizes the speech collected by the microphone; a command control unit which issues a command for controlling the device, based on the speech recognized by the first speech recognition unit; and a control unit which prohibits the command issuance unit from issuing the command, based on the speech to be output from the loudspeaker. 17-. (canceled)8. A device including a speech recognition function which recognizes user speech which is speech from a user , the device comprising:a loudspeaker which outputs speech to a space;a microphone which collects speech in the space;a speech output unit configured to output a speech signal;a first speech recognition unit configured to recognize the speech collected by the microphone;a first control unit configured to generate a command for controlling the speech output unit, based on the speech recognized by the first speech recognition unit; anda second control unit configured to permit or prohibit issuance of the command to the speech output unit, based on the speech signal,wherein the second control unit includes a second speech recognition unit configured to analyze the speech signal to recognize the speech to be output from the loudspeaker, andthe second control unit is configured to determine whether or not the speech recognized by the second speech recognition unit matches a predetermined keyword, and when the speech recognized by the second speech recognition unit matches the predetermined keyword, prohibit the issuance of the command and when the speech recognized by the second speech recognition unit does not match the predetermined keyword, permit issuance of the command.9. A method of recognizing user speech using a device including a speech recognition function , the user speech being ...

Подробнее
Номер записи: 15
04-01-2018 дата публикации

AUDIO QUALITY IMPROVEMENT IN MULTIMEDIA SYSTEMS

Номер: US20180005642A1
Автор: Wang Wenjie
Принадлежит:

Methods and systems are disclosed for echo suppression of an input audio signal. A multimedia system and a remote control unit are configured to adaptively and dynamically preform calibration processes for obtaining sets of echo suppression parameters. The sets of echo suppression parameters are used to generate an audio signal from an input audio. When rendered by a speaker, the generated audio signal produces echo-suppressed sound of the input audio signal at one of more locations. 1. A method for echo suppression in an audio system , comprising:receiving by the audio system a first echo suppression request message;causing, by the audio system, a speaker to generate a first acoustic pulse within a first predetermined time period after receiving the first echo suppression request message, wherein the first acoustic pulse has a pulse width smaller than a first sound resolution time period and travels along a first direct path and a first set of one or more indirect paths to reach a remote electronic device at a first location;receiving, by the audio system, a first data message associated with the first echo suppression request message from the remote electronic device containing a first set of data, wherein the first set of data relates to sound reflections in an environment with the audio system, is to be used for echo suppression, and corresponds to a first signal generated by a microphone in the remote electronic device upon detecting by the microphone the first acoustic pulse from the first direct path and from the first set of one or more indirect paths following the detection of the first acoustic pulse from the first direct path by the microphone;receiving by the audio system a primary audio signal from a multimedia source;generating by the audio system an echo suppression audio signal, wherein the echo suppression audio signal is derived from the primary audio signal with a time adjustment, an amplitude adjustment, and a phase shift determined from at least ...

Подробнее
Номер записи: 16
02-01-2020 дата публикации

CALL QUALITY IMPROVEMENT SYSTEM, APPARATUS AND METHOD

Номер: US20200005806A1
Автор: CHOI Hyeon Sik, LEE Keun Sang, SEO Jae Pil
Принадлежит:

Provided is a call quality improvement method configured to operate a call quality improvement system and a call quality improvement apparatus by executing an artificial intelligence (AI) algorithm and/or a machine learning algorithm in a 5G environment connected for the Internet of Things. According to one embodiment of the present disclosure, the call quality improvement method may include receiving a voice signal from a far-end speaker, receiving a sound signal including a voice signal from a near-end speaker, receiving an image of a face of the near-end speaker, including lips, and extracting the voice signal of the near-end speaker from the received sound signal. 1. A call quality improvement system using lip-reading , the call quality improvement system comprising:a microphone configured to collect a sound signal including a voice signal of a near-end speaker;a speaker configured to output a voice signal from a far-end speaker;a camera configured to photograph a face of the near-end speaker, including lips; anda sound processor configured to extract the voice signal of the near-end speaker from the sound signal collected from the microphone,wherein the sound processor comprises an echo reduction module including an adaptive filter configured to filter out an echo component from the sound signal collected through the microphone based on a signal inputted to the speaker, and a filter controller configured to control the adaptive filter, andthe filter controller changes parameters of the adaptive filter based on lip movement information of the near-end speaker.2. The call quality improvement system according to claim 1 , wherein the sound processor further comprises:a noise reduction module configured to reduce a noise signal in the sound signal from the echo reduction module; anda voice reconstructor configured to reconstruct the voice signal of the near-end speaker damaged during a noise reduction process through the noise reduction module, based on the lip ...

Подробнее
Номер записи: 17
02-01-2020 дата публикации

MICROPHONE ARRAY PROCESSING FOR ADAPTIVE ECHO CONTROL

Номер: US20200005807A1
Автор: ALLEN Justin L., KOVVALI Narayan
Принадлежит:

An apparatus includes a beamformer, an echo suppression control unit, and a residual echo cancellation unit. The beamformer is configured to pass desired portions of audio signals and to suppress undesired portions of the audio signals. The beamformer includes a speech blocking filter to prevent suppression of near-end desired talker speech in the audio signals and an echo suppression filter to suppress echo in the audio signals. An echo suppression control unit is coupled to the beamformer and receives signals and determines whether to dynamically adapt the speech blocking filter or to dynamically adapt the echo suppression filter. The speech blocking filter remains unchanged during dynamic adaptation of the echo suppression filter, and the echo suppression filter remains unchanged during dynamic adaptation of the speech blocking filter. The residual echo cancellation unit is coupled to the beamformer and receives output audio signals from the beamformer and further suppresses residual echo. 1. An apparatus comprising:a beamformer configured to pass desired portions of audio signals received using two or more microphones and further configured to suppress undesired portions of the audio signals, wherein the beamformer comprises a speech blocking filter to prevent suppression of near-end desired talker speech in the audio signals and further comprises an echo suppression filter to suppress echo from the audio signals;an echo suppression control unit coupled to the beamformer, wherein the echo suppression control unit is configured to receive a signal and determine whether to dynamically adapt the speech blocking filter or to dynamically adapt the echo suppression filter, wherein the speech blocking filter remains unchanged during dynamic adaptation of the echo suppression filter and wherein the echo suppression filter remains unchanged during dynamic adaptation of the speech blocking filter; anda residual echo cancellation unit coupled to the beamformer, wherein the ...

Подробнее
Номер записи: 18
07-01-2016 дата публикации

Speakerphone and/or Microphone Arrays and Methods and Systems of Using the Same

Номер: US20160007114A1
Автор: Robert Henry Frater
Принадлежит: Individual

The present disclosure is directed to devices, methods and systems for microphone arrays wherein enhancing performance of directional microphone arrays is provided. Enhanced performance of speaker phones is also provided. In certain embodiments, the housing of the device is configured to support the at least three microphones and the loudspeaker in a substantially first orientation; and the at least three microphones and the loudspeaker are arranged in a spatial relationship such that appropriate phase and delay characteristics achieve a substantial null response in the at least three microphones and in the loudspeaker in a substantial vertical direction away from the substantially first orientation over a desired audible range of frequencies and the device is able to provide a response to sounds over a range of first oriented elevations.

Подробнее
Номер записи: 19
07-01-2021 дата публикации

Microphone array device, conference system including microphone array device and method of controlling a microphone array device

Номер: US20210006897A1
Автор: Logemann Fabian, Rasumow Eugen, Rieck Sebastian, Werner Jens
Принадлежит:

A microphone array device including microphone capsules and at least one processing unit configured to receive output signals of the microphone capsules, dynamically steer an audio beam based on the received output signal of the microphone capsules, and generate and provide an audio output signal based on the received output signal of the microphone capsules. The processing unit is configured to operate in a dynamic beam mode where at least one focused audio beam is formed that points towards a detected audio source and in a default beam mode where a broader audio beam is formed that covers substantially a default detection area. The microphone array may be incorporated into a conference system. 2. The microphone array device of claim 1 , wherein the processing unit comprises:a beam forming unit adapted for combining output signals of the microphone capsules to form an audio beam;a direction detection unit for detecting an audio source direction from the received output signal of the microphone capsules;a direction control unit for controlling the beam forming unit to point the audio beam to the detected direction; anda mode control unit for controlling the operation of the microphone array device in one of said at least two different modes.3. The microphone array device of claim 2 , wherein:the mode control unit switches to the default beam mode if the mode control signal indicates that an audio signal is reproduced via said at least one loudspeaker in the detection area and switches to the dynamic beam mode otherwise.4. The microphone array device of claim 1 , further comprising a memory for storing beam forming parameters to be used in the default beam mode.5. The microphone array device of claim 1 , wherein the default detection area is a maximum detection area of the microphone array device.6. The microphone array device of claim 1 , wherein the focused audio beam is adapted to cover a single person and the default audio beam is adapted to cover a plurality of ...

Подробнее
Номер записи: 20
04-01-2018 дата публикации

BI-MAGNITUDE PROCESSING FRAMEWORK FOR NONLINEAR ECHO CANCELLATION IN MOBILE DEVICES

Номер: US20180007482A1
Автор: Huang Yiteng, Luebs Alejandro, Skoglund Jan
Принадлежит:

Techniques of performing acoustic echo cancellation involve providing a bi-magnitude filtering operation that performs a first filtering operation when a magnitude of an incoming audio signal to be output from a loudspeaker is less than a specified threshold and a second filtering operation when the magnitude of the incoming audio signal is greater than the threshold. The first filtering operation may take the form of a convolution between the incoming audio signal and a first impulse response function. The second filtering operation may take the form of a convolution between a nonlinear function of the incoming audio signal and a second impulse response function. For such a convolution, the bi-magnitude filtering operation involves providing, as the incoming audio signal, samples of the incoming audio signal over a specified window of time. The first and second impulse response functions may be determined from an input signal input into a microphone. 1. A method , comprising:receiving, by processing circuitry configured to reduce acoustic echo in an audio system including a loudspeaker and a microphone, at the loudspeaker of the audio system, an audio signal from a source location remote from the audio system;performing, by the processing circuitry, a comparison operation on a magnitude of the audio signal and a threshold magnitude to produce a comparison result; performing, by the processing circuitry, a first filtering operation on an input signal into the microphone of the audio system to produce a first filtered input signal; and', 'transmitting, by the processing circuitry, the first filtered input signal to the source location;, 'in response to the comparison result indicating that the magnitude of the audio signal is less than the threshold magnitude performing, by the processing circuitry, a second filtering operation on the input signal into the microphone of the audio system to produce a second filtered input signal, the second filtered input signal being ...

Подробнее
Номер записи: 21
14-01-2016 дата публикации

WIND NOISE REDUCTION FOR AUDIO RECEPTION

Номер: US20160012828A1
Автор: Chatlani Navin, Plante Fabrice M., Saplakoglu Gurhan
Принадлежит:

Wind noise reduction is described for audio signals received in a device. In one embodiment, an audio signal is decomposed into a plurality of sub-bands, the audio signal including wind noise, a first sub-band of the plurality of sub-bands low-pass filtered, wind noise is removed from the first sub band and the first sub-band is combined with the other sub-bands after removing wind noise. 1. A method comprising:decomposing an audio signal into a plurality of sub-bands, the audio signal including wind noise;low-pass filtering a first sub-hand of the plurality of sub-hands;removing wind noise from the first sub-band after low-pass filtering; andcombining the first sub-band with the other sub-bands of the plurality of sub-hands after removing wind noise.2. The method of claim 1 , wherein the audio signal is sampled at a first sampling rate claim 1 , the method further comprising:down sampling the first sub-band to a second sampling rate before removing wind noise; andup sampling the first sub-band to the first sampling rate after removing the wind noise.3. The method of claim 2 , further comprising low-pass filtering the first sub-band after upsampling.4. The method of claim 3 , wherein low-pass filtering the first sub-band before removing wind noise and low-pass filtering after up sampling are both performed at the same low pass filter cutoff frequency.5. The method of claim 4 , wherein the low-pass filtering cutoff frequency is selected to be above a wind noise frequency.6. The method of claim 1 , wherein decomposing comprises applying the audio signal to a crossover filter that produces the plurality of sub-bands.7. The method of claim 1 , wherein the audio signal comprises a stream of digital samples received from a microphone and a digital-to-analog converter.8. The method of claim 7 , wherein the digital samples have a first sampling frequency claim 7 , the method further comprising down sampling the first sub-band to a second sampling rate lower than the first ...

Подробнее
Номер записи: 22
11-01-2018 дата публикации

METHOD AND SYSTEM FOR MULTI-TALKER BABBLE NOISE REDUCTION

Номер: US20180012614A1
Автор: LANDSBERGER David M., SELESNICK Ivan W., SOLEYMANI Roozbeh
Принадлежит:

A system and method for improving intelligibility of speech is provided. The system and method may include obtaining an input audio signal frame, classifying the input audio signal frame into a first category or a second category, wherein the first category corresponds to the noise being stronger than the speech signal, and the second category corresponds to the speech signal being stronger than the noise, decomposing the input audio signal frame into a plurality of sub-band components; de-noising each sub-band component of the input audio signal frame in parallel by applying a first wavelet de-noising method including a first wavelet transform and a predetermined threshold for the sub-band component, and a second wavelet de-noising method including a second wavelet transform and the predetermined threshold for the sub-band component, wherein the predetermined threshold for each sub-band component is based on at least one previous noise-dominant signal frame received by the receiving arrangement. 1. A method for reduction of noise , comprising:receiving from a receiving arrangement an input audio signal frame comprising a speech signal and a noise;classifying the input audio signal frame into a first category or a second category, wherein the first category corresponds to the noise being stronger than the speech signal, and the second category corresponds to the speech signal being stronger than the noise;decomposing the input audio signal frame into a plurality of sub-band components; andde-noising each sub-band component of the input audio signal frame in parallel by applying a first wavelet de-noising method including a first wavelet transform and a predetermined threshold for the sub-band component, and a second wavelet de-noising method including a second wavelet transform and the predetermined threshold for the sub-band component, wherein the predetermined threshold for each sub-band component is based on at least one previous noise-dominant signal frame ...

Подробнее
Номер записи: 23
14-01-2021 дата публикации

DETECTION AND RESTORATION OF DISTORTED SIGNALS OF BLOCKED MICROPHONES

Номер: US20210012787A1
Автор: CHI Sanghyun, Peters Nils Günther, Salehin S M Akramus, Thagadur Shivappa Shankar
Принадлежит:

Methods, systems, and devices for mitigating audio interference are described. The methods, systems, and devices may relate to monitoring a parameter associated with an audio signal received by at least a first microphone of multiple microphones of a device, determining that the monitored parameter associated with the audio signal exceeds a threshold by comparing the monitored parameter to the threshold, determining an acoustic path interference associated with the monitored parameter based on the monitored parameter exceeding the threshold, the acoustic path interference including a physical interference in an acoustic path to at least the first microphone, and implementing a restoration process to mitigate the acoustic path interference based on determining the acoustic path interference associated with the monitored parameter. 1. A method for mitigating audio interference , comprising:monitoring a parameter associated with an audio signal received by at least a first microphone of multiple microphones of a device;determining that the monitored parameter associated with the audio signal exceeds a threshold by comparing the monitored parameter to the threshold;determining an acoustic path interference associated with the monitored parameter based at least in part on the monitored parameter exceeding the threshold, the acoustic path interference comprising a physical interference in an acoustic path to at least the first microphone; andimplementing a restoration process to mitigate the acoustic path interference based at least in part on determining the acoustic path interference associated with the monitored parameter.2. The method of claim 1 , further comprising:capturing, as part of an ambisonic audio capture based at least in part on implementing the restoration process, the audio signal from the first microphone and at least an audio signal of a second microphone from the multiple microphones.3. The method of claim 1 , wherein determining that the monitored ...

Подробнее
Номер записи: 24
14-01-2021 дата публикации

AUDIO ALERT AUDIBILITY ESTIMATION METHOD AND SYSTEM

Номер: US20210012788A1
Автор: Every Mark Robert, KARIMIAN AZARI Sam
Принадлежит:

A method and system of estimating human perception of audibility of audio alerts in the presence of background noise. In the audibility estimation system, a microphone generates an input signal corresponding to an audio alert. A processor receives the input signal and generates an audibility metric representing human perception of audibility of the audio alert based on a comparison between a background noise estimate and an audio alert estimate, and causes an action to be taken based on the audibility metric. 1. A method of estimating human perception of the audibility of an audio alert in the presence of a background noise , the method comprising: obtaining an input signal from a microphone,', 'obtaining, from an audio alert generation system for generating the audio alert, a real-time stream including a reference signal corresponding to the audio alert as the audio alert is being generated by the audio alert generation system,', 'obtaining from the input signal, using the reference signal, a background noise estimate and audio alert estimate represented at the microphone,', 'generating an audibility metric representing human perception of audibility of the audio alert based on a comparison between the background noise estimate and the audio alert estimate; and, 'in an alert audibility estimation system,'}taking an action based on the audibility metric.2. The method of claim 1 , wherein the comparison is a short-time cross correlation comparison.3. The method of claim 1 , wherein the comparison is based on a signal-to-noise ratio of the audio alert estimate to the background noise estimate.4. The method of claim 1 , wherein generating the audibility metric is further based on a frequency-weighting that correlates with human perception of relative loudness.5. (canceled)6. The method of claim 1 , wherein obtaining the background noise estimate is based on adaptively filtering the audio alert from the input signal using the reference signal.7. The method of claim 1 , ...

Подробнее
Номер записи: 25
14-01-2021 дата публикации

SYSTEM AND METHOD FOR REDUCING DISTORTION AND ECHO LEAKAGE IN HANDS-FREE COMMUNICATION

Номер: US20210012789A1
Автор: Every Mark Robert, HUSAIN Mohammad Aamir, Linseisen Frank, Percy Michael Andrew
Принадлежит: 2236008 Ontario Inc.

A method of echo cancellation in hands-free communication is disclosed. The method includes: receiving, via a receive signal processor, a far-end audio signal; providing the far-end audio signal to: an acoustic echo canceller module as a reference signal, and at least one loudspeaker for playback; determining an external gain value associated with the far-end audio signal, the external gain applied to the far-end audio signal downstream of the receive signal processor and prior to playback from the at least one loudspeaker; adjusting at least one parameter of the acoustic echo canceller module based on the external gain value; receiving playback output of the far-end audio signal from the at least one loudspeaker as an input signal to a microphone; and processing the microphone input signal by the adjusted acoustic echo canceller module to produce an echo-cancelled signal. 1. A method of echo cancellation in hands-free communication , the method comprising:receiving, via a receive signal processor, a far-end audio signal; an acoustic echo canceller module as a reference signal, and', 'at least one loudspeaker for playback;, 'providing the far-end audio signal todetermining an external gain value associated with the far-end audio signal, the external gain applied to the far-end audio signal downstream of the receive signal processor and prior to playback from the at least one loudspeaker;adjusting at least one parameter of the acoustic echo canceller module based on the external gain value;receiving an input signal to a microphone containing echo of the far-end signal played from the at least one loudspeaker; andprocessing the microphone input signal by the adjusted acoustic echo canceller module to produce an echo-cancelled signal.2. The method of claim 1 , wherein determining the external gain value comprises determining a current external playback volume associated with the at least one loudspeaker claim 1 , the method further comprising:performing, by the receive ...

Подробнее
Номер записи: 26
03-02-2022 дата публикации

VOICE-CONTROLLED ELECTRONIC FAUCET, VOICE-CONTROLLED ELECTRONIC FAUCET ASSEMBLY, AND VOICE-CONTROLLED ELECTRONIC FAUCET MODULE

Номер: US20220034075A1
Автор: TZENG Rong-Chyan
Принадлежит:

A voice-controlled electronic faucet assembly includes an electronic mixing valve fluidly connected to a cold water source and a hot water source; a spout; and a control module. The spout is fluidly connected to the electronic mixing valve. The control module without networking function includes a sound receiving component, an echo elimination unit and a processing unit. The sound receiving component receives a sound. The echo elimination unit is coupled to the sound receiving component and processes an echo elimination on the sound. The processing unit is coupled to the echo elimination unit and receives an audio signal after processing with the echo elimination, and performs an offline voice recognition on the audio signal based on a database and generates a comparison result, and outputs a control signal for controlling the electronic mixing valve to perform a corresponding action according to the comparison result. 1. A voice-controlled electronic faucet assembly including:an electronic mixing valve, fluidly connected to a cold water source and a hot water source;a spout, fluidly connected to the electronic mixing valve; anda control module, without networking function, the control module including a sound receiving component, an echo elimination unit and a processing unit, the sound receiving component receiving a sound, the echo elimination unit coupled to the sound receiving component and processing an echo elimination to the sound, and the processing unit coupled to the echo elimination unit and receiving an audio signal after processing with the echo elimination;wherein the processing unit performs an offline voice recognition on the audio signal based on a database and generates a comparison result, and the processing unit outputs a control signal to the electronic mixing valve according to the comparison result for controlling the electronic mixing valve to perform an action correspondingly.2. The voice-controlled electronic faucet assembly as claimed in ...

Подробнее
Номер записи: 27
21-01-2016 дата публикации

VOICE INFORMATION CONTROL METHOD AND TERMINAL DEVICE

Номер: US20160019894A1
Автор: SHIMADA Isao, TSUJIKAWA MISAKI
Принадлежит:

A voice information control method for a terminal used in a system including a server device which creates text data on the basis of the voice information received from the terminal device, the method including: acquiring plurality items of first voice information; specifying a time interval that includes second voice information which is one of the plurality items of the first voice information, and which includes spoken voice of a first speaker who uses the first terminal device; and transmitting the second voice information included in the specified time interval being transmitted to the server device.

Подробнее
Номер записи: 28
21-01-2016 дата публикации

Adaptive Vehicle State-Based Hands-Free Phone Noise Reduction With Learning Capability

Номер: US20160019904A1
Автор: Amman Scott Andrew, Charette Francois, Cooprider Anthony Dwayne, Gur Yuksel, Nicastri Paul J Joseph, Puskorius Gintaras Vincent
Принадлежит:

This disclosure generally relates to a system, apparatus, and method for achieving an adaptive vehicle state-based hands free noise reduction feature. A noise reduction tool is provided for adaptively applying a noise reduction strategy on a sound input that uses feedback speech quality measures and machine learning to develop future noise reduction strategies, where the noise reduction strategies include analyzing vehicle operational state information and external information that are predicted to contribute to cabin noise and selecting noise reducing pre-filter options based on the analysis. 1. An apparatus , comprising:a memory configured to store a noise reduction pre-filter and feedback data; receive a sound input;', 'receive training input data;', 'receive the feedback data;', 'determine whether to select the pre-filter based on the training input data and feedback data, and', 'if the pre-filter is selected, apply the selected pre-filter to the sound input., 'a processor in communication with the memory, the processor configured to2. The apparatus of claim 1 , wherein the processor is further configured to:apply a Weiner filter to the sound input after the selected pre-filter has been applied.3. The apparatus of claim 1 , wherein the processor is further configured to:generate a performance measure on the sound input after the selected pre-filter has been applied, wherein the performance measure indicates a speech quality of the sound input after the selected pre-filter has been applied.4. The apparatus of claim 3 , wherein the performance measure is a signal-to-noise measure that identifies an energy level for a speech signal within the sound input after the selected pre-filter has been applied.5. The apparatus of claim 3 , wherein the processor is further configured to:feedback the performance measure as new feedback data, andcause the new feedback data to be stored in the memory.6. The apparatus of claim 1 , wherein the training input data includes vehicle ...

Подробнее
Номер записи: 29
21-01-2016 дата публикации

SPEECH PROCESSING SYSTEM

Номер: US20160019905A1
Автор: Stylianou Ioannis
Принадлежит: KABUSHIKI KAISHA TOSHIBA

A speech intelligibility enhancing system for enhancing speech to be outputted in a noisy environment, the system comprising: a speech input for receiving speech to be enhanced; a noise input for receiving real-time information concerning the noisy environment; an enhanced speech output to output said enhanced speech; and a processor configured to convert speech received from said speech input to enhanced speech to be output by said enhanced speech output, the processor being configured to: apply a spectral shaping filter to the speech received via said speech input; apply dynamic range compression to the output of said spectral shaping filter; and measure the signal to noise ratio at the noise input, wherein the spectral shaping filter comprises a control parameter and the dynamic range compression comprises a control parameter and wherein at least one of the control parameters for the dynamic range compression or the spectral shaping is updated in real time according to the measured signal to noise ratio.

Подробнее
Номер записи: 30
21-01-2016 дата публикации

System For Automatic Speech Recognition And Audio Entertainment

Номер: US20160019907A1
Автор: Buck Markus, Haulick Tim, SUHADI Suhadi, Wolff Tobias
Принадлежит: NUANCE COMMUNICATIONS, INC.

In one aspect, the present application is directed to a device for providing different levels of sound quality in an audio entertainment system. The device includes a speech enhancement system with a reference signal modification unit and a plurality of acoustic echo cancellation filters. Each acoustic echo cancellation filter is coupled to a playback channel. The device includes an audio playback system with loudspeakers. Each loudspeaker is coupled to a playback channel. At least one of the speech enhancement system and the audio playback system operates according to a full sound quality mode and a reduced sound quality mode. In the full sound quality mode, all of the playback channels contain non-zero output signals. In the reduced sound quality mode, a first subset of the playback channels contains non-zero output signals and a second subset of the playback channels contains zero output signals. 1. A device for providing different levels of sound quality in an audio entertainment system , the device comprising:a speech enhancement system with a reference signal modification unit and a plurality of acoustic echo cancellation filters, each acoustic echo cancellation filter being coupled to a playback channel; andan audio playback system with loudspeakers, each loudspeaker being coupled to a playback channel,wherein at least one of the speech enhancement system and the audio playback system operates according to:i) a full sound quality mode, during which all of the playback channels contain non-zero output signals, andii) a reduced sound quality mode, during which a first subset of the playback channels contains non-zero output signals and a second subset of the playback channels contains zero output signals.2. The device of claim 1 , wherein the audio playback system activates all the playback channels during the full sound quality mode and activates a subset of the playback channels during the reduced sound quality mode.3. The device according to claim 2 , ...

Подробнее
Номер записи: 31
21-01-2016 дата публикации

ACOUSTIC ECHO MITIGATION APPARATUS AND METHOD, AUDIO PROCESSING APPARATUS AND VOICE COMMUNICATION TERMINAL

Номер: US20160019909A1
Автор: Dickins Glenn N., SHI DONG, Sun Xuejing
Принадлежит: DOLBY LABORATORIES LICENSING CORPORATION

The present application provides an acoustic echo mitigation apparatus and method, an audio processing apparatus and a voice communication terminal. According to an embodiment, an acoustic echo mitigation apparatus is provided, including: an acoustic echo canceller for cancelling estimated acoustic echo from a microphone signal and outputting an error signal; a residual echo estimator for estimating residual echo power; and an acoustic echo suppressor for further suppressing residual echo and noise in the error signal based on the residual echo power and noise power. Here, the residual echo estimator is configured to be continuously adaptive to power change in the error signal. According to the embodiments of the present application, the acoustic echo mitigation apparatus and method can, at least, be well adaptive to the change of power of the error signal after the AEC processing, such as that caused by change of double-talk status, echo path properties, noise level and etc.

Подробнее
Номер записи: 32
19-01-2017 дата публикации

Audio processing system and audio processing method thereof

Номер: US20170018282A1
Автор: Chien-Hung Chen, Shih-Lung Tsai
Принадлежит: Chunghwa Picture Tubes Ltd

An audio processing system and an audio processing method thereof are provided. A first audio signal and at least one second audio signal from different directions are received by audio receivers. A first component signal and a second component signal are calculated by separating the first audio signal. A third component signal and a fourth component signal are calculated by separating the second audio signal. A major voice information is obtained by calculating the first component signal and the third component signal. A non-major voice information is obtained by calculating the second component signal and the fourth component signal. The non-major voice information is subtracted from the first audio signal to obtain a calculation result. The calculation result and the major voice information are added to obtain a major voice signal in the first audio signal and the at least one second audio signal.

Подробнее
Номер записи: 33
03-02-2022 дата публикации

REVERBERATION COMPENSATION FOR FAR-FIELD SPEAKER RECOGNITION

Номер: US20220036903A1
Автор: Biswal Narayan, Cilingir Gokcen
Принадлежит:

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 ...

Подробнее
Номер записи: 34
03-02-2022 дата публикации

Filtering method, filtering device, and storage medium stored with filtering program

Номер: US20220036910A1
Автор: Ryo Tanaka, Satoshi Ukai
Принадлежит: Yamaha Corp

A filtering method includes: receiving a first audio signal and a second audio signal that include sound emitted from a same sound source at different volumes; generating a filter signal by convoluting adaptive filter coefficients into the second audio signal; removing components of the filter signal from the first audio signal; and limiting a gain of the adaptive filter coefficients to 1.0 or less.

Подробнее
Номер записи: 35
18-01-2018 дата публикации

Assessment and Adjustment of Audio Installation

Номер: US20180018984A1
Автор: Dickins Glenn N., Holmberg Paul, SHI DONG
Принадлежит: DOLBY LABORATORIES LICENSING CORPORATION

Example embodiments disclosed herein relate to assessment and adjustment for an audio environment. A computer-implemented method is provided. The method includes obtaining a first audio signal captured by a device located in an environment. The method also includes analyzing a characteristic of the first audio signal to determine an acoustic performance metric for the environment. The method further includes, in response to the acoustic performance metric being below a threshold, providing a first task for a user to perform based on the characteristic of the first audio signal. The first task is related to an adjustment to a setting of the environment. Embodiments in this regard further provide a corresponding computer program product. Corresponding system and computer program product are also disclosed. 1. A computer-implemented method comprising:obtaining a first audio signal captured by a device located in an environment;analyzing a characteristic of the first audio signal to determine an acoustic performance metric for the environment; andin response to the acoustic performance metric being below a threshold, providing a first task for a user to perform based on the characteristic of the first audio signal, the first task being related to an adjustment to a setting of the environment.2. The method of claim 1 , further comprisingextracting a noise signal from the first audio signal; andplaying back the extracted noise signal by a speaker.3. The method of claim 2 , wherein the first task is related to addition claim 2 , adjustment or removal of physical objects within the environment.4. The method of claim 1 , further comprising:providing an acoustical or optical indication of the performance metric to the user, wherein the performance metric indicates whether the acoustic performance has improved or deteriorated.5. The method of claim 1 , wherein the first audio signal is captured by spatial microphones of the device claim 1 , the method further ...

Подробнее
Номер записи: 36
16-01-2020 дата публикации

APPARATUS FOR POST-PROCESSING AN AUDIO SIGNAL USING A TRANSIENT LOCATION DETECTION

Номер: US20200020349A1
Автор: Disch Sascha, GAMPP Patrick, HAVENSTEIN Julia, Hellmuth Oliver, HERRE JÜRGEN, KARAMPOURNIOTIS Antonios, PROKEIN Peter, Richter Daniel, UHLE Christian
Принадлежит:

Apparatus for post-processing an audio signal, including: a converter for converting the audio signal into a time-frequency representation; a transient location estimator for estimating a location in time of a transient portion using the audio signal or the time-frequency representation; and a signal manipulator for manipulating the time-frequency representation, wherein the signal manipulator is configured to reduce or eliminate a pre-echo in the time-frequency representation at a location in time before the transient location or to perform a shaping of the time-frequency representation at the transient location to amplify an attack of the transient portion. 1. An apparatus for post-processing an audio signal , comprising:a converter for converting the audio signal into a time-frequency representation;a transient location estimator for estimating a location in time of a transient portion using the audio signal or the time-frequency representation; anda signal manipulator for manipulating the time-frequency representation, wherein the signal manipulator is configured to reduce or eliminate a pre-echo in the time-frequency representation at a location in time before the transient location or to perform a shaping of the time-frequency representation at the transient location to amplify an attack of the transient portion.2. The apparatus of claim 1 ,wherein the signal manipulator comprises a tonality estimator for detecting tonal signal components in the time-frequency representation preceding the transient portion in time, andwherein the signal manipulator is configured to apply the pre-echo reduction or elimination in a frequency-selective way, so that at frequencies where tonal signal components have been detected, the signal manipulation is reduced or switched off compared to frequencies where the tonal signal components have not been detected.3. The apparatus of claim 1 , wherein the signal manipulator comprises a pre-echo width estimator for estimating a width in ...

Подробнее
Номер записи: 37
21-01-2021 дата публикации

Echo Cancellation Using A Subset of Multiple Microphones As Reference Channels

Номер: US20210020188A1
Автор: ATKINS Joshua D., DESHPANDE Ashrith, JUKIC Ante, Malik Sarmad Aziz, WUNG Jason
Принадлежит:

An echo canceller is disclosed in which audio signals of the playback content received by one or more of the microphones from a loudspeaker of the device may be used as the playback reference signals to estimate the echo signals of the playback content received by a target microphone for echo cancellation. The echo canceller may estimate the transfer function between a reference microphone and the target microphone based on the playback reference signal of the reference microphone and the signal of the target microphone. To mitigate near-end speech cancellation at the target microphone, the echo canceller may compute a mask to distinguish between target microphone audio signals that are echo-signal dominant and near-end speech dominant. The echo canceller may use the mask to adaptively update the transfer function or to modify the playback reference signal used by the transfer function to estimate the echo signals of the playback content. 1. A method of performing echo cancellation , the method comprising:receiving a reference audio signal, produced by a reference microphone of a device, that is responsive to sound from a loudspeaker of the device;receiving a target audio signal, produced by a first target microphone of the device, that is responsive to an echo of the sound from the loudspeaker and to speech from a speech source;determining a mask based on the reference audio signal and the target audio signal, wherein the mask is a measure of a relative strength of the reference audio signal and the target audio signal;adaptively estimating a transfer function between the reference microphone and a second target microphone based on the mask, the reference audio signal, and the target audio signal, the second target microphone producing an audio signal that is responsive to the echo of the sound from the loudspeaker and the speech from the speech source;determining an estimated echo component of the sound from the loudspeaker based on the estimated transfer function ...

Подробнее
Номер записи: 38
22-01-2015 дата публикации

Method and Apparatus for Acoustic Echo Control

Номер: US20150023514A1
Автор: Dickins Glenn N., HUO JiaQuan, SHI DONG, Sun Xuejing
Принадлежит: DOLBY LABORATORIES LICENSING CORPORATION

Embodiments of method and apparatus for acoustic echo control are described. According to the method, an echo energy-based doubletalk detection is performed to determine whether there is a doubletalk in a microphone signal with reference to a loudspeaker signal. A spectral similarity between spectra of the microphone signal and the loudspeaker signal is calculated. It is determined that there is no doubletalk in the microphone signal if the spectral similarity is higher than a threshold level. Adaption of an adaptive filter for applying acoustic echo cancellation or acoustic echo suppression on the microphone signal is enabled if it is determined that there is no doubletalk in the microphone signal through the echo energy-based doubletalk detection, or there is no doubletalk through the spectral similarity-based doubletalk detection. 122-. (canceled)23. A method of performing acoustic echo control , comprising:performing an echo energy-based doubletalk detection to determine whether there is a doubletalk in a microphone signal with reference to a loudspeaker signal;calculating a spectral similarity between spectra of the microphone signal and the loudspeaker signal;determining that there is no doubletalk in the microphone signal if the spectral similarity is higher than a threshold level; andenabling adaption of an adaptive filter for applying acoustic echo cancellation or acoustic echo suppression on the microphone signal if it is determined that there is no doubletalk in the microphone signal through the echo energy-based doubletalk detection, or there is no doubletalk through the spectral similarity-based doubletalk detection.24. The method according to claim 23 , wherein the calculation of the spectral similarity comprises:calculating each of the spectra as a spectral vector including elements representing signal magnitudes on a set of perceptually spaced bands, or on a set of frequency bins of the corresponding signal; andcalculating the spectral similarity as ...

Подробнее
Номер записи: 39
16-01-2020 дата публикации

CLOUD-BASED ACOUSTIC ECHO CANCELLER

Номер: US20200021329A1
Автор: Schulz Dieter
Принадлежит: Mitel Cloud Services, Inc.

A cloud based echo canceller is set forth for recreating an estimate of a lost packet or data at a server without requiring redundant data over the network or freezing operation of the echo canceller. In an exemplary embodiment, the echo cancelling function is not located in a single device, but is shared between the end-point and a cloud service, where the function of the end-point is to provide a time synchronized copy of the signal from the end-point loudspeaker and the signal received by the end-point microphone. Consequently, the high CPU intensive operations can be offloaded to a server such as a cloud server. In addition, several users can share the echo canceller, thereby reducing the cost of the overall function. According to an additional aspect, a further synchronization block is provided, in the form of a packet estimator, to compensate for packet or data loss in the send direction. 1. A method of compensating for lost packets in a distributed echo canceler , where successive input packets are stored in memory of the distributed echo canceler , comprising:a) detecting a lost signal packet Ro′(n);b) freezing operation of the distributed echo canceler;c) invoking a packet loss compensation (PLC) algorithm for one of either recreating an estimated output packet from previous output packets or halting transmission of output packets;d) estimating the lost signal packet Ro′(n) by performing a correlation of a previously received signal packet with an input signal packet Rin, 'A) upon receipt of a next packet repeating steps b) and c) until effect of the lost signal packet Ro′(n) is flushed out of an echo canceler memory and resuming operation of the distributed echo canceler; or', 'i) if said correlation is poor then'} B) using a relative shift offset of the lost signal packet Ro′(n) to the input signal packet Rin to read an estimated buffer value (Ro″) out of the successive input packets and replacing the signal packet Ro′(n) by the estimated buffer value (Ro ...

Подробнее
Номер записи: 40
26-01-2017 дата публикации

NOISE ELIMINATION CIRCUIT

Номер: US20170025133A1
Автор: Liu Lian
Принадлежит:

A noise elimination circuit of particular application in enhancing vocal clarity in a teleconference includes a first voice processing circuit, a second voice processing circuit, and a subtracter. The first voice processing circuit receives and processes a first voice from a first microphone and the second voice processing circuit receives and processes the same voice from a second microphone (second voice). The first voice and the second voice include voice signals and noises. The subtracter is electrically connected to the two voice processing circuits to receive the first voice and the second voice respectively processed by the first voice processing circuit and the second voice processing circuit. The subtracter substracts the second voice from the first voice, and outputs a clear voice from which noise has been eliminated. 1. A noise elimination circuit , comprising:a first voice processing circuit, configured to receive and process a first voice from a first microphone, and the first voice comprises a first voice signal and a first noise;a second voice processing circuit, configured to receive and process a second voice from a second microphone, and the second voice comprises a second voice signal and a second noise; anda subtracter, coupled to the first voice processing circuit and the second voice processing circuit, configured to receive the first voice and the second voice processed by the first voice processing circuit and the second voice processing circuit, and to subtract the second voice from the first voice to output a voice signal without noises.2. The noise elimination circuit of claim 1 , wherein the subtracter comprises a first integrated operational amplifier claim 1 , having a first input port coupled to a first voice processing circuit output port; and having a second input port coupled to a second voice processing circuit output port and a first integrated operational amplifier output port.3. The noise elimination circuit of claim 1 , wherein ...

Подробнее
Номер записи: 41
28-01-2016 дата публикации

AUDIO SIGNAL ANALYSIS

Номер: US20160027421A1
Автор: CURCIO Igor Danilo Diego, Eronen Antti Johannes, HELANDER Elina Elisabet, Leppänen Jussi Artturi, MAHKONEN Katariina Jutta, POPA Victor, VIRTANEN Tuomas Oskari
Принадлежит:

An apparatus comprises a dereverberation module for generating a dereverberated audio signal based on an original audio signal containing reverberation, and an audio-analysis module for generating audio analysis data based on audio analysis of the original audio signal and audio analysis of the dereverberated audio signal. 150-. (canceled)51. A method comprising:generating a dereverberated audio signal based on an original audio signal containing reverberation; andgenerating audio analysis data based on audio analysis of the original audio signal and audio analysis of the dereverberated audio signal.52. The method of claim 51 , comprising performing audio analysis using the original audio signal and the dereverberated audio signal.53. The method of claim 51 , comprising performing audio analysis on one of original audio signal and the dereverberated audio signal based on results of the audio analysis of the other one of the original audio signal and the dereverberated audio signal.54. The method of claim 53 , comprising performing audio analysis on the original audio signal based on results of the audio analysis of the dereverberated audio signal.55. The method of claim 51 , comprising generating the dereverberated audio signal based on results of the audio analysis of the original audio signal.57. The method of claim 56 , comprising performing beat period determination analysis on the dereverberated audio signal and performing beat time determination analysis on the original audio signal.58. The method of claim 57 , comprising performing beat time determination analysis on the original audio signal based on results of the beat period determination analysis.59. The method of claim 51 , comprising analysing the original audio signal to determine if the original audio signal is derived from speech or from music and performing the audio analysis in respect of the dereverberated audio signal based on the determination as to whether the original audio signal is derived ...

Подробнее
Номер записи: 42
25-01-2018 дата публикации

OPTIMIZATION OF SPEECH INPUT FOR MULTIPLE SPEECH AGENTS USED IN A COMMON APPLICATION ENVIRONMENT

Номер: US20180025740A1
Автор: Burk Michael T.
Принадлежит:

An automotive speech input optimization method includes using a microphone to convert audible speech into an audio signal. A selection of a speech agent is received. Spectral matching is performed on the audio signal to produce a conditioned audio signal. The spectral matching is dependent upon the selection of the speech agent. The conditioned audio signal is input to the selected speech agent. 1. An automotive speech input optimization method , comprising the steps of:using a microphone to convert audible speech into an audio signal;receiving a selection of a speech agent;performing spectral matching on the audio signal to produce a conditioned audio signal, the spectral matching being dependent upon the selection of the speech agent; andinputting the conditioned audio signal to the selected speech agent.2. The method of wherein the microphone converts audible speech within a passenger compartment of a motor vehicle into the audio signal.3. The method of comprising the further step of performing signal conditioning on the audio signal before the spectral matching.4. The method of comprising the further step of performing beamforming on the audio signal before the spectral matching.5. The method of comprising the further step of performing echo cancellation on the audio signal before the spectral matching.6. The method of comprising the further step of performing noise reduction on the audio signal before the spectral matching.7. The method of wherein the selected speech agent comprises Siri claim 1 , Google claim 1 , Nuance claim 1 , Scan Speak claim 1 , or Watson.8. The method of wherein the spectral matching is performed specific to the selected speech agent.9. The method of wherein the spectral matching is initiated in response to the selected speech agent being called upon for interaction.10. An automotive speech input optimization arrangement claim 1 , comprising:a microphone configured to convert audible speech into an audio signal; receive a selection of a ...

Подробнее
Номер записи: 43
28-01-2016 дата публикации

VEHICLE IN CABIN SOUND PROCESSING SYSTEM

Номер: US20160029111A1
Автор: Biemer Michael, Wacquant Sylvie
Принадлежит:

A sound system of a vehicle includes a plurality of microphones disposed in a cabin of the vehicle, a plurality of speakers disposed in the cabin of the vehicle, and a sound processor operable to process microphone output signals of the microphones to determine a voice signal of a speaking occupant in the vehicle at or near one of the microphones. The sound processor generates a processor output signal that is provided to at least some of the speakers. Responsive to the processor output signal, the at least some of the speakers generate sound representative of the voice signal of the speaking occupant to direct the sound towards other occupants in the vehicle, while one or more speakers at or near the seat occupied by the speaking occupant do not generate sound representative of the voice signal of the speaking occupant. 1. A sound system of a vehicle , said sound system comprising:a plurality of microphones disposed in a cabin of a vehicle equipped with said sound system;a plurality of speakers disposed in the cabin of the equipped vehicle at or near respective seats of the equipped vehicle;a sound processor operable to process microphone output signals of said microphones to determine a voice signal of a speaking occupant in the equipped vehicle at or near one of said microphones;wherein said sound processor generates a processor output signal that is provided to at least some of said speakers; andwherein, responsive to said processor output signal, said some of said speakers generate sound representative of the voice signal of the speaking occupant to direct the sound towards at least some of the other occupants in the equipped vehicle while one or more speakers at or near the seat occupied by the speaking occupant do not generate sound representative of the voice signal of the speaking occupant so as to not direct the sound towards the speaking occupant.2. The sound system of claim 1 , comprising a plurality of microphones exterior of the cabin of the equipped ...

Подробнее
Номер записи: 44
10-02-2022 дата публикации

SPEECH PROCESSING METHOD AND METHOD FOR GENERATING SPEECH PROCESSING MODEL

Номер: US20220044678A1
Автор: BAI Jinfeng, Chen Xu, HAN Runqiang, Jia Lei
Принадлежит:

The present disclosure provides a speech processing method, and a method for generating a speech processing model, related to a field of signal processing technologies. The speech processing method includes: obtaining M speech signals to be processed and N reference signals; performing sub-band decomposition on each of the M speech signals and each of the N reference signals to obtain frequency-band components in each speech signal and each reference signal; processing the frequency-band components in each speech signal and each reference signal by using an echo cancellation model, to obtain an ideal ratio mask corresponding to the N reference signals in each frequency band of each speech signal; and performing echo cancellation on each frequency-band component of each speech signal based on the ideal ratio mask corresponding to the N reference signals in each frequency band of each speech signal, to obtain M echo-cancelled speech signals. 1. A speech processing method , comprising:obtaining M speech signals to be processed and N reference signals, wherein M and N are positive integers equal to or greater than 1;performing sub-band decomposition on each of the M speech signals and each of the N reference signals to obtain frequency-band components in each speech signal and frequency-band components in each reference signal;processing the frequency-band components in each speech signal and the frequency-band components in each reference signal by using an echo cancellation model, to obtain an ideal ratio mask (IRM) corresponding to the N reference signals in each frequency band of each speech signal; andperforming echo cancellation on each frequency-band component of each speech signal based on the ideal ratio mask corresponding to the N reference signals in each frequency band of each speech signal, to obtain M echo-cancelled speech signals.2. The speech processing method according to claim 1 , wherein performing sub-band decomposition on each of the M speech ...

Подробнее
Номер записи: 45
24-01-2019 дата публикации

ECHO DELAY TRACKING METHOD AND APPARATUS

Номер: US20190027160A1
Автор: LIANG Junbin
Принадлежит:

An echo delay tracking method includes obtaining, by a computing terminal, a current frame reference signal and a current frame collection signal; and identifying target frequency information in the current frame collection signal according to signal-to-noise ratios of the current frame collection signal at a plurality of frequencies. The target frequency information includes at least one target frequency that corresponds to a signal-to-noise ratio greater than a first preset threshold. The method also includes determining whether the current frame collection signal is a valid frame signal based on the target frequency information; and if yes, performing a cross-correlation operation of a signal component of the current frame reference signal corresponding to the target frequency and a signal component of the current frame collection signal corresponding to the target frequency. An echo delay value can be obtained according to a result of the cross-correlation operation. 1. An echo delay tracking method , comprising:obtaining, by a computing terminal, a current frame reference signal related to an audio output device of the computing terminal and a current frame collection signal collected by an audio input device of the computing terminal;identifying, by the computing terminal, target frequency information in the current frame collection signal according to signal-to-noise ratios of the current frame collection signal at a plurality of frequencies, the target frequency information comprising at least one target frequency and each target frequency corresponding to a signal-to-noise ratio greater than a first preset threshold;determining, by the computing terminal, whether the current frame collection signal is a valid frame signal satisfying a preset condition based on the target frequency information;in response to determining that the current frame collection signal is a valid frame signal satisfying the preset condition, performing a cross-correlation operation ...

Подробнее
Номер записи: 46
28-01-2021 дата публикации

NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM FOR STORING DETECTION PROGRAM, DETECTION METHOD, AND DETECTION APPARATUS

Номер: US20210027796A1
Автор: MORIOKA Kiyonori, Nakayama Sayuri, Togawa Taro
Принадлежит: FUJITSU LIMITED

A detection method implemented by a computer, the detection method includes: acquiring voice information containing voices of a plurality of speakers; detecting a first speech segment of a first speaker among the plurality of speakers included in the voice information based on a first acoustic feature of the first speaker, the first acoustic feature being obtained by performing a machine learning; and detecting a second speech segment of a second speaker among the plurality of speakers based on a second acoustic feature, the second acoustic feature being an acoustic feature included in the voice information associated with a predetermined time range, the predetermined time range being a time range outside the first speech segment. 1. A non-transitory computer-readable storage medium for storing a detection program which causes a processor to perform processing , the processing comprising:acquiring voice information containing voices of a plurality of speakers;detecting a first speech segment of a first speaker among the plurality of speakers included in the voice information based on a first acoustic feature of the first speaker, the first acoustic feature being obtained by performing a machine learning; anddetecting a second speech segment of a second speaker among the plurality of speakers based on a second acoustic feature, the second acoustic feature being an acoustic feature included in the voice information associated with a predetermined time range, the predetermined time range being a time range outside the first speech segment.2. The non-transitory computer-readable storage medium according to claim 1 , whereinthe detecting of a first speech segment is configured to detect the first speech segment based on a similarity of the learned acoustic feature to an acoustic feature included in the voice information.3. The non-transitory computer-readable storage medium according to claim 1 , causing the computer to execute the processing further comprising:updating ...

Подробнее
Номер записи: 47
24-01-2019 дата публикации

ACOUSTICAL METHOD FOR DETECTING SPEAKER MOVEMENT

Номер: US20190028824A1
Автор: Freeman Eric, Gaalaas Joseph
Принадлежит:

Audio speaker systems and methods are provided to detect movement of the speaker system or other device. An audio program content signal is converted into an acoustic signal, and the acoustic signal causes an echo signal. The echo signal is received and a relationship of the echo signal to the audio program content signal is quantified. A quantified value is compared to a stored quantified value and, based upon the comparison, a change in physical position is selectively indicated. 1. A method of detecting movement of a device , the method comprising:receiving an audio program content signal;converting the audio program content signal into an acoustic signal;receiving an echo signal;quantifying a relationship between the echo signal and the audio program content signal to provide a quantified value;comparing the quantified value to a stored quantified value; andmodifying an array processing parameter based at least in part upon the comparison.2. The method of wherein quantifying a relationship between the echo signal and the audio program content signal includes determining filter coefficients of an echo cancellation system.3. (canceled)4. (canceled)5. The method of wherein quantifying a relationship between the echo signal and the audio program content signal includes performing at least one of a cross-correlation claim 1 , a least mean squares algorithm claim 1 , a normalized least mean squares algorithm claim 1 , and a recursive least square algorithm.6. (canceled)7. The method of further comprising prompting a user to reconfigure the device based at least in part upon the comparison.8. An audio speaker system comprising:an input to receive an audio signal;an acoustic transducer coupled to the input to receive the audio signal and to convert the audio signal into an acoustic signal;an adaptive filter coupled to the input to receive the audio signal, and configured to receive an echo signal and to estimate a transfer function between the input and the echo; anda ...

Подробнее
Номер записи: 48
23-01-2020 дата публикации

Pre-distortion system for cancellation of nonlinear distortion in mobile devices

Номер: US20200028970A1
Автор: Dimitrios Dimitriadis, Donald J. Bowen, Horst J. Schroeter, Lusheng Ji
Принадлежит: AT&T INTELLECTUAL PROPERTY I LP

A pre-distortion system for improved mobile device communications via cancellation of nonlinear distortion is disclosed. The pre-distortion system may transmit an acoustic signal from a network to a device, wherein the acoustic signal includes a linear signal and a nonlinear cancellation signal that cancels at least a portion of nonlinear distortions created once a loudspeaker in the device emits the linear signal. Thus, when a loudspeaker of a mobile device is operating and nonlinear distortions are generated by the loudspeaker or adjacent components of the mobile device in close proximity to the loudspeaker, the pre-distortion system may create one or more nonlinear cancellation signals in the network. The nonlinear cancellation signal may be combined with the linear signal sent to the loudspeaker to cancel the nonlinear distortion signal created by the loudspeaker emitting acoustic sounds from the linear signal. Thus, the nonlinear cancellation signal becomes a pre-distortion signal.

Подробнее
Номер записи: 49
23-01-2020 дата публикации

AUDIO DEVICE AND COMPUTER READABLE PROGRAM

Номер: US20200029162A1
Автор: Matsunaga Keishi
Принадлежит:

[Problem] To provide an audio device capable of further reliably accepting voice control even during playback. [Solution] An audio device comprises: a parameter determination unit that determines an echo-back parameter for canceling a wraparound signal that enters voice-control microphones -- as the audio from a speaker during playback; a filter processing unit that performs filtering using the echo-back parameter for audio signals collected by the voice-control microphones -- during playback; a voice recognition unit that performs voice recognition processing for a filtered audio signal; and an operation acceptance unit that accepts voice control on the basis of the voice recognition results. The parameter determination unit outputs a test signal from a speaker and collects the test signal through the voice-control microphones --, and determines the echo-back parameter on the basis of the delay time and the attenuation rate of the collected audio signal relative to the test signal. 1. An audio device having a function of receiving a voice operation , the audio device comprising:audio reproduction means for reproducing an audio signal to output the audio signal to a speaker;a voice operation reception microphone configured to receive a voice operation from a user;parameter determination means for determining an echo back parameter for canceling a diffracted signal that is output from the speaker to the voice operation reception microphone in a diffracted manner during audio reproduction;filter processing means for filtering a sound signal collected by the voice operation reception microphone during audio reproduction with the echo back parameter determined by the parameter determination means; andvoice operation reception means for executing voice recognition processing for the collected sound signal filtered by the filter processing means to receive the voice operation, output a test signal from the speaker;', 'collect the test signal by the voice operation ...

Подробнее
Номер записи: 50
04-02-2016 дата публикации

SPEECH DEREVERBERATION METHODS, DEVICES AND SYSTEMS

Номер: US20160035367A1
Автор: Dickins Glenn N., GOESNAR Erwin, GUNAWAN David
Принадлежит: DOLBY LABORATORIES LICENSING CORPORATION

Improved audio data processing method and systems are provided. Some implementations involve dividing frequency domain audio data into a plurality of subbands and determining amplitude modulation signal values for each of the plurality of subbands. A band-pass filter may be applied to the amplitude modulation signal values in each subband, to produce band-pass filtered amplitude modulation signal values for each subband. The band-pass filter may have a central frequency that exceeds an average cadence of human speech. A gain may be determined for each subband based, at least in part, on a function of the amplitude modulation signal values and the band-pass filtered amplitude modulation signal values. The determined gain may be applied to each subband. 151-. (canceled)52. A method , comprising:receiving a signal that includes frequency domain audio data;applying a filterbank to the frequency domain audio data to produce frequency domain audio data in a plurality of subbands;determining amplitude modulation signal values for the frequency domain audio data in each subband;applying a band-pass filter to the amplitude modulation signal values in each subband to produce band-pass filtered amplitude modulation signal values for each subband, the band-pass filter having a central frequency that exceeds an average cadence of human speech;determining a gain for each subband based, at least in part, on a function of the amplitude modulation signal values and the band-pass filtered amplitude modulation signal values; andapplying a determined gain to each subband.53. The method of claim 52 , wherein the process of determining amplitude modulation signal values involves determining log power values for the frequency domain audio data in each subband.54. The method of claim 52 , wherein a band-pass filter for a lower-frequency subband passes a larger frequency range than a band-pass filter for a higher-frequency subband.55. The method of claim 52 , wherein the band-pass filter ...

Подробнее
Номер записи: 51
17-02-2022 дата публикации

Automated Clinical Documentation System and Method

Номер: US20220051772A1
Автор: Almendro Barreda Daniel Paulino, Erskine Garret N., Gallopyn Guido Remi Marcel, Jost Uwe Helmut, Naylor Patrick, Nour-Eldin Amr, Owen Donald E., Öz Mehmet Mert, Sharma Dushyant
Принадлежит:

A computer-implemented method, computer program product, and computing system for source separation is executed on a computing device and includes obtaining encounter information of a user encounter, wherein the encounter information includes first audio encounter information obtained from a first encounter participant and at least second audio encounter information obtained from at least a second encounter participant. The first audio encounter information and the at least second audio encounter information are processed to eliminate audio interference between the first audio encounter information and the at least second audio encounter information. 1. A computer-implemented method for source separation , executed on a computing device , comprising:obtaining encounter information of a user encounter, wherein the encounter information includes first audio encounter information obtained from a first encounter participant and at least second audio encounter information obtained from at least a second encounter participant; andprocessing the first audio encounter information and the at least second audio encounter information to eliminate audio interference between the first audio encounter information and the at least second audio encounter information.2. The computer-implemented method of wherein the user encounter includes one or more of:a financial encounter;a life coach encounter;a legal encounter;a telecom encounter;a retail encounter; anda business encounter.3. The computer-implemented method of wherein the encounter information includes one or more of:financial information;life coach information;legal information;telecom information;retail information; andbusiness information.4. The computer-implemented method of wherein the computer-implemented method is executed within one or more of:a financial environment;a life coach environment;a legal environment;a telecom environment;a retail environment; anda business environment.5. The computer-implemented method of ...

Подробнее
Номер записи: 52
01-02-2018 дата публикации

Detecting Signal Processing Component Failure Using One or More Delay Estimators

Номер: US20180035223A1
Автор: Vicinus Patrick, Volcker Björn
Принадлежит:

One or more delay estimators are used to detect failure in a signal processing component, such as an acoustic echo canceller. A first delay estimator is used to generate i) an estimated post-processing delay between when a known audio signal was conveyed to a loudspeaker, and when a portion of the processed audio signal that includes the known audio signal was output from the signal processing component, and ii) a confidence level for the estimated post-processing delay. A failure of the signal processing component may be detected in response to the estimated post-processing delay exceeding a threshold. A second delay estimator may also be used to generate an estimated pre-processing delay and a confidence level for the estimated pre-processing delay for comparison to the estimated post-processing delay and confidence level for the estimated post-processing delay in order to provide further failure detection accuracy and specificity. 1. A method of detecting failure of an acoustic echo cancelling component in an endpoint device , the method comprising:conveying a known audio signal i) to a loudspeaker communicably coupled to the endpoint device, wherein the loudspeaker outputs the known audio signal as sound, and ii) to a post-processing delay estimator;conveying a processed audio signal to the post-processing delay estimator, wherein the post-processing audio signal is generated by the acoustic echo cancelling component in response to a microphone audio signal received by the acoustic echo cancelling component from a microphone communicably coupled to the endpoint device;calculating, by the post-processing delay estimator in response to the known audio signal and the processed audio signal, an estimated post-processing delay that is an estimate of an amount of time between conveying the known audio signal to the loudspeaker and outputting of a portion of the processed audio signal that includes the known audio signal from the acoustic echo cancelling component; ...

Подробнее
Номер записи: 53
31-01-2019 дата публикации

AUDIO PROCESSING FOR SPEECH

Номер: US20190035415A1
Автор: Bojan Luigi, Kalluri Ravi, Lu Youhong, Walters Andrew
Принадлежит:

A method, a device, and a non-transitory storage medium are described in which a power of late reverberation of a speech signal is estimated based on early samples of the speech signal. The power of the late reverberation may be subtracted linearly or non-linearly from the speech signal. 1. A method comprising:receiving, by a microphone of a device and from a user, a speech signal, wherein the speech signal includes an early reverberation portion and a late reverberation portion, and wherein the early reverberation portion includes a direct coupling portion in which a path of the user's speech to the device travels a shortest distance to the device and an early reflection portion;transforming, by a filter of the device, the speech signal to a time and frequency domain signal;filtering, by the filter of the device, the time and frequency domain signal based on a frequency band included in the time and frequency domain signal;estimating, by a de-reverber of the device, a power of the late reverberation portion based on a filtered early reverberation portion and a segment of the speech signal in which the user's speech has stopped;subtracting, by the de-reverber, the estimated power of the late reverberation portion from the speech signal based on the estimating; andoutputting, by the de-reverber, a resultant speech signal based on the subtracting.2. The method of claim 1 , wherein the subtracting is performed linearly.3. The method of claim 1 , wherein the subtracting is performed non-linearly.4. (canceled)5. The method of claim 1 , wherein the estimating further comprises:selecting, by the de-reverber of the device, the segment of the speech signal in which the user's speech has stopped;calculating, by the de-reverber of the device, a first power of a first point in the segment;calculating, by the de-reverber of the device, a second power of a second point in the segment that occurs subsequent to the first point; andestimating, by the de-reverber of the device, an ...

Подробнее
Номер записи: 54
31-01-2019 дата публикации

SINGLE CHANNEL NOISE REDUCTION

Номер: US20190035416A1
Автор: Christoph Markus
Принадлежит:

One embodiment id directed towards a noise reduction system that includes a detector block that is configured to detect noise components in an input signal based on a signal-to-noise ratio spectrum of the input signal. The noise reduction system also includes a masking block operatively coupled with the detector block and configured to generate a final spectral noise removal mask and to apply the final spectral noise removal mask to the input signal if noise components in the input signal are detected, the final spectral noise removal mask being configured to suppress the noise components in the input signal, when applied. 1. A noise reduction system , comprising:a detector block configured to detect noise components in an input signal based on a signal-to-noise ratio spectrum of the input signal; anda masking block operatively coupled to the detector block and configured to generate a final spectral noise removal mask and to apply the final spectral noise removal mask to the input signal if noise components in the input signal are detected, the final spectral noise removal mask being configured to suppress the noise components in the input signal, when applied.2. The system of claim 1 , wherein the detector block comprises a signal-to-noise ratio determination block that is configured to determine the signal-to-noise ratio spectrum of the input signal by determining signal-to-noise ratios per discrete frequency of the input signal.3. The system of claim 1 , wherein the masking block comprises:a first evaluation block configured to generate from the signal-to-noise ratio spectrum of the input signal a basic spectral noise removal mask, the first evaluation block further configured to compare the signal-to-noise ratio spectrum of the input signal to a predetermined signal-to-noise ratio threshold and to provide a weighting mask dependent on the results of the comparison; anda mask modification block configured to modify the basic spectral noise removal mask dependent ...

Подробнее
Номер записи: 55
30-01-2020 дата публикации

MITIGATING ANOMALOUS SOUNDS

Номер: US20200035254A1
Автор: Bender Michael, Boss Gregory J., Childress Rhonda L.
Принадлежит:

Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: activating a streaming media recording buffer that records streaming media of an online conference, the online conference having first second and third user online conference participant users; examining data to return an action decision, the examining data to return an action decision including examining data of the streaming media recording buffer to identify an anomalous sound represented in the recorded media stream data of the streaming media recording buffer; returning an action decision based on the examining data to return an action decision, the action decision being an action to mitigate the anomalous sound; and providing one or more output to mitigate the anomalous sound in accordance with the returned action decision. 1. A computer-implemented method comprising:activating a streaming media recording buffer that records streaming media of an online conference, the online conference having first second and third user online conference participant users;examining data to return an action decision, the examining data to return an action decision including examining data of the streaming media recording buffer to identify an anomalous sound represented in the recorded media stream data of the streaming media recording buffer;returning an action decision based on the examining data to return an action decision, the action decision being an action to mitigate the anomalous sound; andproviding one or more output to mitigate the anomalous sound in accordance with the returned action decision.2. The computer-implemented method of claim 1 , wherein the examining data to return an action decision is responsive to feedback data being received by a user participant of the first second and third online conference user participants.3. The computer-implemented method of claim 1 , wherein the providing one or more output is activated ...

Подробнее
Номер записи: 56
31-01-2019 дата публикации

Annoyance Noise Suppression

Номер: US20190037301A1
Автор: Klimanis Gints, Parks Anthony
Принадлежит: DOLBY LABORATORIES LICENSING CORPORATION

Personal audio systems and methods are disclosed. A personal audio system includes a voice activity detector to determine whether or not an ambient audio stream contains voice activity, a pitch estimator to determine a frequency of a fundamental component of an annoyance noise contained in the ambient audio stream, and a filter bank to attenuate the fundamental component and at least one harmonic component of the annoyance noise to generate a personal audio stream. The filter bank implements a first filter function when the ambient audio stream does not contain voice activity, or a second filter function when the ambient audio stream contains voice activity. 1 determine a current context of a user associated with the personal audio system;', 'retrieve one or more candidate annoyance noise classes from a sound database based on the determined current context;', 'configure a first filter function to identify a set of expected annoyance noises based on the retrieved one or more candidate annoyance noise classes;', 'determine a frequency of a fundamental component of an annoyance noise contained in the ambient audio stream, wherein the annoyance noise is one of the set of expected annoyance noises and corresponds to a specific source;', 'implement the first filter function when the ambient audio stream does not contain voice activity, wherein the first filter function is configured to attenuate the fundamental component and at least one harmonic component of the annoyance noise; and', 'implement a second filter function, different from the first filter function, when the ambient audio stream contains voice activity, wherein the second filter function is configured to attenuate the annoyance noise in one or more frequency bands that the annoyance noise overlaps with a voice associated with the voice activity; and, 'a processor coupled to an active acoustic filter configured to receive an ambient audio stream, the processor is configured toa memory coupled to the ...

Подробнее
Номер записи: 57
04-02-2021 дата публикации

METHOD AND DEVICE OF SUSTAINABLY UPDATING COEFFICIENT VECTOR OF FINITE IMPULSE RESPONSE FILTER

Номер: US20210035593A1
Автор: Liang Min
Принадлежит:

A method and a device of sustainably updating a coefficient vector of a finite impulse response FIRfilter. The method includes obtaining () a time-varying regularization factor used for iteratively updating the coefficient vector of the FIR filter in a case that the coefficient vector of the FIR filter is used for processing a preset signal; updating () the coefficient vector of the FIR filter according to the time-varying regularization factor. 172.-. (canceled)73. A sustainable adaptive updating method of a coefficient vector of a Finite Impulse Response (FIR) filter , comprising:obtaining a time-varying regularization factor used for iteratively updating the coefficient vector of the FIR filter in a case that the coefficient vector of the FIR filter is used for processing a preset signal;updating the coefficient vector of the FIR filter according to the time-varying regularization factor.74. The sustainable adaptive updating method according to claim 73 , wherein the preset signal comprises one of combined pairs of following:a far-end reference speech signal inputted in an Acoustic Echo Canceller (AEC) and a near-end speech signal received by a microphone;a noise reference signal and a system input signal in an adaptive noise cancellation system;an interference reference signal and a system input signal in an adaptive interference cancellation system; andan excitation input signal and an unknown system output signal to be identified in adaptive system identification.75. The sustainable adaptive updating method according to claim 73 , wherein the preset signal comprises a far-end reference speech signal inputted in an Acoustic Echo Canceller (AEC) and a near-end speech signal received by a microphone;obtaining the time-varying regularization factor used for iteratively updating the coefficient vector of the FIR filter in a case that the coefficient vector of the FIR filter is used for processing the preset signal, comprises:obtaining a power of a signal received ...

Подробнее
Номер записи: 58
11-02-2016 дата публикации

NOISE SUPPRESSING DEVICE, NOISE SUPPRESSING METHOD, AND A NON-TRANSITORY COMPUTER-READABLE RECORDING MEDIUM STORING NOISE SUPPRESSING PROGRAM

Номер: US20160042746A1
Автор: FUJIEDA Masaru
Принадлежит: OKI ELECTRIC INDUSTRY CO., LTD.

There is provided a noise suppressing device for suppress a noise component included in an input signal. The noise suppressing device comprises: a noise estimating unit configured to estimate a noise spectrum based on an input spectrum obtained by performing a frequency analysis on the input signal; a speech-likelihood calculating unit configured to calculate speech-likelihood based on the input spectrum and the noise spectrum; a suppression-gain calculating unit configured to calculate first suppression gain based on the input spectrum and the noise spectrum; a suppression-gain combining unit configured to calculate third suppression gain by combining the first suppression gain and second suppression gain, which is provided as a predetermined constant value or provided by smoothing the first suppression gain, based on the speech-likelihood; and a multiplying unit obtaining an output spectrum by multiplying the input spectrum by the third suppression gain. 1. A noise suppressing device for suppress a noise component included in an input signal , the noise suppressing device comprising:a noise estimating unit configured to estimate a noise spectrum based on an input spectrum obtained by performing a frequency analysis on the input signal;a speech-likelihood calculating unit configured to calculate speech-likelihood based on the input spectrum and the noise spectrum;a suppression-gain calculating unit configured to calculate first suppression gain based on the input spectrum and the noise spectrum;a suppression-gain combining unit configured to calculate third suppression gain by combining the first suppression gain and second suppression gain, which is provided as a predetermined constant value or provided by smoothing the first suppression gain, based on the speech-likelihood; anda multiplying unit obtaining an output spectrum by multiplying the input spectrum by the third suppression gain.2. The noise suppressing device according to claim 1 ,wherein the speech- ...

Подробнее
Номер записи: 59
11-02-2016 дата публикации

VOICE SWITCHING DEVICE, VOICE SWITCHING METHOD, AND NON-TRANSITORY COMPUTER-READABLE RECORDING MEDIUM HAVING STORED THEREIN A PROGRAM FOR SWITCHING BETWEEN VOICES

Номер: US20160042747A1
Автор: Endo Kaori
Принадлежит:

A voice switching device includes a learning unit configured to learn a background noise model expressing background noise contained in a first voice signal, based on the first voice signal, while the first voice signal having a first frequency band is received; a pseudo noise generation unit configured to generate pseudo noise expressing noise in a pseudo manner, based on the background noise model, after a first time point when the first voice signal is last received in a case where a received voice signal is switched from the first voice signal to a second voice signal having a second frequency band narrower than the first frequency band; and a superimposing unit configured to superimpose the pseudo noise on the second voice signal after the first time point. 1. A voice switching device comprising:a learning unit configured to learn a background noise model expressing background noise contained in a first voice signal, based on the first voice signal, while the first voice signal having a first frequency band is received;a pseudo noise generation unit configured to generate pseudo noise expressing noise in a pseudo manner, based on the background noise model, after a first time point when the first voice signal is last received in a case where a received voice signal is switched from the first voice signal to a second voice signal having a second frequency band narrower than the first frequency band; anda superimposing unit configured to superimpose the pseudo noise on the second voice signal after the first time point.2. The voice switching device according to claim 1 , further comprising:a voiceless time interval detection unit configured to detect a voiceless time interval in which reception of the second voice signal is not started after the first time point, whereinthe pseudo noise generation unit generates the pseudo noise over the entire first frequency band in the voiceless time interval, andthe superimposing unit superimposes the pseudo noise generated ...

Подробнее
Номер записи: 60
09-02-2017 дата публикации

Echo-Cancelling Device and Echo-Cancelling Method

Номер: US20170040026A1
Автор: Chen Manu, Chen Yan-Ren, Chiu Pin-Feng, Chu Yung-Ching, Kuo Yan-Min, Wang Hsi-Pang
Принадлежит:

An echo-cancelling device includes an audio input/output (I/O) terminal, an audio-receiving module, an analog-to-digital (A/D) converter, and a processor is provided. The A/D converter is electrically connected to the audio-receiving module. The processor is electrically connected to the A/D converter and the audio I/O terminal. The audio I/O terminal receives an external reference signal from an electronic device. The audio-receiving module receives an input audio and an output audio from the electronic device, and generates an analog input signal having the input audio and the output audio. The A/D converter generates a digital input signal according to the analog input signal. The processor cancels the output audio to generate a second (digital) sound signal according to the digital input signal and the external reference signal. Finally, the processor transmits the second (digital) sound signal to the electronic device via the audio I/O terminal. 1. An echo-cancelling device , which is electrically connected to an electronic device , wherein an output signal and an external reference signal are generated by the electronic device according to a first sound signal , and an output audio is generated by the electronic device according to the output signal , comprising:an audio input-output (I/O) terminal receives the external reference signal;an audio-receiving module receives an input audio and the output audio, and generates an analog input signal with the input audio and the output audio;an analog-to-digital (A/D) converter is electrically connected to the audio-receiving module to receive the analog input signal and generates a digital input signal according to the analog input signal; anda processor is electrically connected to the A/D converter and the audio I/O terminal to receive the external reference signal via the audio I/O terminal and receive the digital input signal from the A/D converter so as to cancel the output audio and generate a second sound ...

Подробнее
Номер записи: 61
12-02-2015 дата публикации

Wired and wireless earset using ear-insertion-type microphone

Номер: US20150043741A1
Автор: Doo Sik Shin
Принадлежит: Individual

The present invention relates to an earset, comprising: a first earphone portion, which includes a first speaker for outputting sound signals or voice signals that are provided from an external device, and which can be inserted into a first external auditory canal of a user; a second earphone portion, which includes a first microphone for receiving inputted user voice signals that are provided through the external auditory canal of the user, and which can be inserted into a second auditory canal of the user; and a main body connected to each of the first and the second earphone portion. When the main body is wirelessly connected to the external device, the main body comprises; a signal transceiving portion for transceiving the signals with the external device; and a control portion for outputting via the first speaker the voice signals received from the external device through the signal transceiving portion.

Подробнее
Номер записи: 62
08-02-2018 дата публикации

SYSTEM AND METHOD FOR PERFORMING SPEECH ENHANCEMENT USING A DEEP NEURAL NETWORK-BASED SIGNAL

Номер: US20180040333A1
Автор: ATKINS Joshua D., Giacobello Daniele, Pishehvar Ramin, WUNG Jason
Принадлежит:

Method for performing speech enhancement using a Deep Neural Network (DNN)-based signal starts with training DNN offline by exciting a microphone using target training signal that includes signal approximation of clean speech. Loudspeaker is driven with a reference signal and outputs loudspeaker signal. Microphone then generates microphone signal based on at least one of: near-end speaker signal, ambient noise signal, or loudspeaker signal. Acoustic-echo-canceller (AEC) generates AEC echo-cancelled signal based on reference signal and microphone signal. Loudspeaker signal estimator generates estimated loudspeaker signal based on microphone signal and AEC echo-cancelled signal. DNN receives microphone signal, reference signal, AEC echo-cancelled signal, and estimated loudspeaker signal and generates a speech reference signal that includes signal statistics for residual echo or for noise. Noise suppressor generates a clean speech signal by suppressing noise or residual echo in the microphone signal based on speech reference signal. Other embodiments are described. 1. A system for performing speech enhancement using a Deep Neural Network (DNN)-based signal comprising:a loudspeaker to output a loudspeaker signal, wherein the loudspeaker is being driven by a reference signal;at least one microphone to receive at least one of: a near-end speaker signal, an ambient noise signal, or the loudspeaker signal and to generate a microphone signal;an acoustic-echo-canceller (AEC) to receive the reference signal and the microphone signal, and to generate an AEC echo-cancelled signal;a loudspeaker signal estimator to receive the microphone signal and the AEC echo-cancelled signal and to generate an estimated loudspeaker signal; anda deep neural network (DNN) to receive the microphone signal, the reference signal, the AEC echo-cancelled signal, and the estimated loudspeaker signal, and to generate a clean speech signal,wherein the DNN is trained offline by exciting the at least one ...

Подробнее
Номер записи: 63
08-02-2018 дата публикации

Vowel Sensing Voice Activity Detector

Номер: US20180040338A1
Автор: Schiro Arthur Leland
Принадлежит: Plantronics, Inc.

Methods and apparatuses for detecting user speech are described. In one example, a method for detecting user speech includes receiving a microphone output signal corresponding to sound received at a microphone and identifying a spoken vowel sound in the microphone signal. The method further includes outputting an indication of user speech detection responsive to identifying the spoken vowel sound. 1. A method for detecting user speech comprising:receiving a microphone output signal corresponding to sound received at a microphone;converting the microphone output signal to a digital audio signal;identifying a spoken vowel sound in the sound received at the microphone from the digital audio signal; andoutputting an indication of user speech detection responsive to identifying the spoken vowel sound.2. The method of claim 1 , further comprising filtering out a low frequency stationary noise below 300 Hz present in the sound.3. The method of claim 2 , wherein the stationary noise comprises heating claim 2 , ventilation claim 2 , and air conditioning (HVAC) noise.4. The method of claim 1 , further comprising:outputting a stationary noise comprising a sound masking noise in an open space, wherein the microphone is disposed in proximity to a ceiling area of the open space and the sound masking noise is present in the sound received at the microphone, wherein identifying the spoken vowel sound is immune to the presence of the sound masking noise.5. The method of claim 1 , wherein identifying the spoken vowel sound in the sound received at the microphone from the digital audio signal comprises detecting harmonic frequency signal components.6. The method of claim 5 , wherein the harmonic frequency signal components comprise energy in a plurality of higher frequency harmonics.7. The method of claim 1 , wherein identifying the spoken vowel sound in the sound received at the microphone from the digital audio signal comprises finding a circular autocorrelation of the absolute ...

Подробнее
Номер записи: 64
08-02-2018 дата публикации

STATE-BASED ENDPOINT CONFERENCE INTERACTION

Номер: US20180041639A1
Автор: Dickins Glenn N., GUNAWAN David
Принадлежит: DOLBY LABORATORIES LICENSING CORPORATION

Systems and methods are described for modifying one of far-end signal playback and capture of local audio on an audio device. Frames of both a far-end audio stream and a near-end audio stream may be analyzed using a measure of voice activity, the analyzing producing voice data associated with each frame. Based on the voice data, a conference state may be determined, and one of playback of the far-end audio stream and capture of local audio on an audio device may be modified based on the determined conference state. By associating the likely intent with a predefined state, the device may further cull or remove unwanted or unlikely content from the device input and output. This may have a substantial advantage in allowing for full duplex operation in the case of more meaningful and continuing voice activity, particularly in the case where there are many connected endpoints. 1. A method for modifying one of far-end signal playback and capture of local audio on an audio device during a conference call , the method comprising the steps of:receiving, by an audio device, a far-end audio stream;splitting the received far-end audio stream into a plurality of frames;analyzing each frame using a measure of voice activity to determine if there is voice activity within each frame, the analyzing producing far-end voice data associated with each frame;analyzing frames of a local input audio stream using the measure of voice activity to produce near-end voice data;determining a conference state based on the far-end voice data and the near-end voice data; andbased on the determined conference state, modifying at least one of playback of the far-end audio stream on a speaker of the audio device and capture of local audio on the audio device.2. The method of claim 1 , the determining the conference state comprising:calculating a transaction parameter value based on the far-end voice data and the near-end voice data; andbased on the calculated transaction parameter value, assigning the ...

Подробнее
Номер записи: 65
07-02-2019 дата публикации

ULTRASONIC ATTACK PREVENTION FOR SPEECH ENABLED DEVICES

Номер: US20190043471A1
Автор: Banas Jan, Klinke Piotr, Maziewski Przemyslaw, Pach Pawel, Prysko Jedrzej, Sokolowska-Kostyk Roksana, Stanczak Dominik, Trella Pawel
Принадлежит: Intel Corporation

Techniques are provided for defending against an ultrasonic attack on a speech enabled device. A methodology implementing the techniques according to an embodiment includes detecting voice activity in an audio signal received by the device and generating an ultrasonic jamming signal in response to the detection. The jamming signal is broadcast over a loudspeaker for up to the duration of the detected voice activity to defend against the ultrasonic attack. According to another embodiment, the ultrasonic jamming signal is generated in response to detection of a wake-on-voice key phrase in the received audio signal, and the jamming signal is broadcast over the loudspeaker for a time duration selected to be less than or equal to a time window during which spoken commands are accepted by the device following the wake-on-voice key phrase detection. The jamming signal may include white or colored noise, combinations of tones, and/or a periodic sweep frequency. 1. At least one non-transitory computer readable storage medium having instructions encoded thereon that , when executed by one or more processors , cause a process to be carried out for ultrasonic attack prevention , the process comprising:detecting voice activity in an audio signal received by a speech enabled device;generating an ultrasonic jamming signal in response to the detection; andbroadcasting the ultrasonic jamming signal over a loudspeaker to prevent an ultrasonic attack on the speech enabled device.2. The computer readable storage medium of claim 1 , wherein broadcasting the ultrasonic jamming signal includes broadcasting the ultrasonic jamming signal for a broadcast time duration selected to be less than or equal to a duration of the detected voice activity.3. The computer readable storage medium of claim 1 , wherein the ultrasonic jamming signal comprises a high pass filtered white noise signal claim 1 , the high pass filter configured with a cut-off frequency at 18 kHz.4. The computer readable storage ...

Подробнее
Номер записи: 66
07-02-2019 дата публикации

NEURAL NETWORK BASED TIME-FREQUENCY MASK ESTIMATION AND BEAMFORMING FOR SPEECH PRE-PROCESSING

Номер: US20190043491A1
Автор: Kupryjanow Adam, Lopatka Kuba
Принадлежит: Intel Corporation

Techniques are provided for pre-processing enhancement of a speech signal. A methodology implementing the techniques according to an embodiment includes performing de-reverberation processing on signals received from an array of microphones, the signals comprising speech and noise. The method also includes generating time-frequency masks (TFMs) for each of the signals. The TFMs indicate the probability that a time-frequency component of the signal associated with that TFM element includes speech. The TFM generation is based on application of a recurrent neural network to the signals. The method further includes generating steering vectors based on speech covariance matrices and noise covariance matrices. The TFMs are employed to filter speech components of the signals, for calculation of the speech covariance, and noise components of the signals for calculation of the noise covariance. The method further includes performing beamforming on the signals, based on the steering vectors, to generate the enhanced speech signal. 1. At least one non-transitory computer readable storage medium having instructions encoded thereon that , when executed by one or more processors , cause a process to be carried out for enhancement of a speech signal , the process comprising:performing de-reverberation (DRV) processing on first and second signals received from first and second microphones, respectively, the first and second signals each comprising a combination of speech and noise;generating first and second time-frequency masks (TFMs), each of the first and second TFMs associated with a corresponding one of the DRV processed first and second signals, each of the first and second TFMs comprising elements indicating a probability that a time-frequency component of the DRV processed signal associated with that TFM element includes speech, wherein the TFM generation is based on application of a recurrent neural network (RNN) to the DRV processed first and second signals;generating ...

Подробнее
Номер записи: 67
07-02-2019 дата публикации

SUPPRESSING KEY PHRASE DETECTION IN GENERATED AUDIO USING SELF-TRIGGER DETECTOR

Номер: US20190043494A1
Автор: Czyryba Sebastian, Kurylo Lukasz, Noczynski Tomasz
Принадлежит: Intel Corporation

An example apparatus for suppression of key phrase detection includes an audio receiver to receive generated audio from a loopback endpoint and captured audio from a microphone. The apparatus includes a self-trigger detector to detect a key phrase in the generated audio. The apparatus also includes a detection suppressor to suppress detection of the detected key phrase in the captured audio at a second key detector for a predetermined time in response to detecting the key phrase in the generated audio. 1. An apparatus for suppression of key phrase detection , comprising:an audio receiver to receive generated audio from a loopback endpoint and captured audio from a microphone;a self-trigger detector to detect a key phrase in the generated audio; anda detection suppressor to suppress detection of the detected key phrase in the captured audio at a key phrase detector for a predetermined time in response to detecting the key phrase in the generated audio.2. The apparatus of claim 1 , wherein the generated audio comprises a reference signal.3. The apparatus of claim 1 , wherein the loopback endpoint is to receive the generated audio from a playback endpoint.4. The apparatus of claim 1 , wherein the captured audio comprises an echo corresponding to the generated audio.5. The apparatus of claim 1 , wherein the predetermined time is based on the detected key phrase.6. The apparatus of claim 1 , comprising a processor to perform echo cancellation on the captured audio.7. The apparatus of claim 1 , comprising a processor to perform direct current (DC) removal on the captured audio to remove DC bias.8. The apparatus of claim 1 , comprising a processor to increase gain on the captured audio.9. The apparatus of claim 1 , comprising a processor to perform beamforming on the captured audio.10. The apparatus of claim 1 , comprising a processor to perform noise reduction on the captured audio.11. A method for suppressing key phrase detection claim 1 , comprising:receiving, via a ...

Подробнее
Номер записи: 68
07-02-2019 дата публикации

RELIABLE REVERBERATION ESTIMATION FOR IMPROVED AUTOMATIC SPEECH RECOGNITION IN MULTI-DEVICE SYSTEMS

Номер: US20190043514A1
Автор: Kupryjanow Adam, Maziewski Przemyslaw
Принадлежит: Intel Corporation

A mechanism is described for facilitating multi-device reverberation estimation according to one embodiment. An apparatus of embodiments, as described herein, includes detection and capture logic to facilitate a microphone of a first voice-enabled device of multiple voice-enabled devices to detect a command from a user. The apparatus further includes calculation logic to facilitate a second voice-enabled device and a third voice-enabled device to calculate speech to reverberation modulation energy ratio (SRMR) values based on the command, where the calculation logic us further to estimate reverberation times (RTs) based on the SRMR values. The apparatus further includes decision and application logic to perform dereverberation based on the estimated RTs of the reverberations. 1. An apparatus comprising:detection and capture logic to facilitate a microphone of a first voice-enabled device of multiple voice-enabled devices to detect a command from a user;calculation logic to facilitate a second voice-enabled device and a third voice-enabled device to calculate speech to reverberation modulation energy ratio (SRMR) values based on the command, wherein the calculation logic us further to estimate reverberation times (RTs) based on the SRMR values; anddecision and application logic to perform dereverberation based on the estimated RTs of the reverberations.2. The apparatus of claim 1 , wherein the RTs relate to reverberations associated with one or more of the first claim 1 , second claim 1 , and third voice-enabled devices claim 1 , wherein the first claim 1 , second claim 1 , and third voice-enable devices are coupled with each other over a communication medium including one or more of a proximity network claim 1 , a cloud network claim 1 , and the Internet.3. The apparatus of claim 1 , wherein the first voice-enabled device is further to convert the command into a text-to-speech (TTS) command claim 1 , wherein one of the first claim 1 , second claim 1 , and third ...

Подробнее
Номер записи: 69
07-02-2019 дата публикации

JOINT BEAMFORMING AND ECHO CANCELLATION FOR REDUCTION OF NOISE AND NON-LINEAR ECHO

Номер: US20190043515A1
Автор: COHEN Alejandro, Markovich-Golan Shmuel
Принадлежит: Intel IP Corporation

Techniques are provided for reduction of noise and nonlinear-echo. A methodology implementing the techniques according to an embodiment includes estimating transfer functions (TFs) of echo paths of audio signals received through a microphone array. The audio signals include speech signal, additive noise, and echo, the TF estimation based on the reference signal. The method also includes cancellation of linear components of the echo, based on the echo path TFs. The method further includes estimating an inverse square root of a covariance matrix of the additive noise, whitening the echo cancelled signals, and estimating a speech path RTF associated with the speech signal, based on the whitened echo cancelled signals. The method further includes performing beamforming on the whitened signals (such as weighted MVDR beamforming), based on the echo path TFs, the speech path RTF, and the estimated inverse square root additive noise covariance matrix. 1. A processor-implemented method for reducing noise and echo in an audio signal , the method comprising:estimating, by a processor-based system, a transfer function (TF) of an echo path associated with a received audio signal, the audio signal including a combination of a speech signal, additive noise, and an echo signal, the estimation based on the reference signal;performing, by the processor-based system, cancellation of one or more linear components of the echo signal, based on the echo path TF, to provide an echo cancelled signal;estimating, by the processor-based system, a square root of an inverse of a covariance matrix of the additive noise;whitening, by the processor-based system, the echo cancelled signal;estimating, by the processor-based system, a speech path RTF associated with the speech signal, based on the whitened echo cancelled signal; andperforming, by the processor-based system, beamforming on the whitened echo cancelled signal, based on the echo path TF, the speech path RTF, and the estimated square root ...

Подробнее
Номер записи: 70
07-02-2019 дата публикации

ACTIVE ACOUSTIC ECHO CANCELLATION FOR ULTRA-HIGH DYNAMIC RANGE

Номер: US20190043519A1
Автор: Rosenkiewicz Sebastian
Принадлежит: Intel Corporation

Techniques related to active acoustic echo cancellation are discussed. Such techniques may include generating an audio output signal having a portion thereof corresponding to a first audio frequency range to negate a response of an audio input device to an output from a speaker in a second audio frequency range at a response negation rate and decimating an audio input signal based on the response negation rate to generate a resultant audio input signal. 1. An apparatus comprising:a speaker to generate audio output;an audio input device to receive audio input and to provide an audio input signal responsive to the audio input at a first sampling rate; and generate an audio output signal having at least a portion thereof corresponding to a first audio frequency range, the portion of the audio output signal to negate a response of the audio input device, at a response negation rate, to an output from the speaker in a second audio frequency range, wherein each audio frequency of the first audio frequency range exceeds a maximum audio frequency of the second audio frequency range; and', 'decimate the audio input signal based on the response negation rate to a second sampling rate less than the first sampling rate to generate a resultant audio input signal., 'one or more processors coupled to the speaker and the audio input device, the one or more processors to2. The apparatus of claim 1 , wherein the one or more processors comprise:a conditioning filter to filter a playback audio signal, the playback audio signal comprising a third audio frequency range, using a filter tuned at least in part on the inverse response of the speaker, the audio input device, and an acoustic path to generate a second audio signal; andan oscillator to operate on the second audio signal to generate the portion of the audio output signal corresponding to the first audio frequency range.3. The apparatus of claim 2 , wherein the second audio frequency range comprises the third audio frequency range ...

Подробнее
Номер записи: 71
06-02-2020 дата публикации

MULTI-CHANNEL ACOUSTIC ECHO CANCELLATION

Номер: US20200043460A1
Автор: Kadri Romi, Sereshki Saeed Bagheri
Принадлежит:

A playback device is configured to receive, via a network interface, a source stream of audio including first and second channel streams of audio, and to produce, via respective first and second speaker drivers, a first channel audio output and a second channel audio output. The playback device is also configured to receive, via one or more microphones, a captured stream of audio including first and second portions corresponding to the respective first and second channel audio outputs. The playback device is also configured to combine at least the first channel stream of audio and the second channel stream of audio into a compound audio signal and perform acoustic echo cancellation on the compound audio signal and thereby produce an acoustic echo cancellation output, then to apply the acoustic echo cancellation output to the captured stream of audio and thereby increase a signal-to noise ratio of the captured stream of audio. 1. A playback device comprising:a first speaker driver;at least a second speaker driver;at least one processor;a network interface;a non-transitory computer-readable medium; and receiving, via the network interface, a source stream of audio comprising source audio content to be played back by the playback device, wherein the source audio content comprises a first channel stream of audio and a second channel stream of audio;', 'producing a first channel audio output by playing back, via the first speaker driver, the first channel stream of audio;', 'producing a second channel audio output by playing back, via the second speaker driver, the second channel stream of audio;', 'receiving, via one or more microphones, a captured stream of audio comprising (i) a first portion corresponding to the first channel audio output and (ii) a second portion corresponding to the second channel audio output, wherein the captured stream of audio has a first signal-to-noise ratio;', 'combining at least the first channel stream of audio and the second channel ...

Подробнее
Номер записи: 72
18-02-2021 дата публикации

AUDIO PROCESSING METHOD AND APPARATUS, AND STORAGE MEDIUM

Номер: US20210050010A1
Автор: CUI Shiqi, Feng Xiaochuan, HAN Wei, Li Dan, LU Kanghong, Qin Bin, Wang Gang, Yang Rui
Принадлежит: BEIJING XIAOMI MOBILE SOFTWARE CO., LTD.

An audio processing method includes: acquiring first audio data associated with a first audio signal after waking up a target application; when second audio data associated with a second audio signal is detected in the process of acquiring the first audio data, acquiring the second audio data; and obtaining target audio data according to the first audio data and the second audio data. With the method, a conversation flow can be simplified without waking up a target application again, the first audio data and the second audio data are combined to obtain target audio data, and audio response is made to the target audio data, which can more accurately get real needs of a user, reduce the rate of isolated responding errors, and improve the accuracy of the audio response. 1. A method for audio processing , applicable to an electronic device , the method comprising:acquiring first audio data associated with a first audio signal, after waking up a target application;in response to that second audio data associated with a second audio signal is detected in the process of acquiring the first audio data, acquiring the second audio data; andobtaining target audio data according to the first audio data and the second audio data.2. The method of claim 1 , further comprising:determining a time difference between end of acquiring the first audio data and start of acquiring the second audio data,wherein the obtaining the target audio data according to the first audio data and the second audio data comprises:obtaining, when the time difference is greater than or equal to a first set duration, the target audio data according to the first audio data and the second audio data.3. The method of claim 2 , wherein the obtaining claim 2 , when the time difference is greater than or equal to the first set duration claim 2 , the target audio data according to the first audio data and the second audio data comprises:detecting, when the time difference is greater than or equal to the first set ...

Подробнее
Номер записи: 73
07-02-2019 дата публикации

MULTI-CHANNEL RESIDUAL ECHO SUPPRESSION

Номер: US20190045065A1
Автор: Bou Daher Elie, Hera Cristian M., Jain Ankita D.
Принадлежит:

Audio systems and methods for suppressing residual echo are provided. First and second audio program content signals are received, and a residual signal from an echo canceler is received. A first spectral mismatch is determined based at least upon a cross power spectral density of the first program content signal and the residual signal. A second spectral mismatch is determined based at least upon a cross power spectral density of the second program content signal and the residual signal. The residual signal is filtered to reduce residual echo, based at least upon the first spectral mismatch, the second spectral mismatch, a spectral density of the first program content signal, a spectral density of the second program content signal, and a spectral density of the residual signal. 1. A method of suppressing residual echo , comprising:receiving a residual signal from an echo cancelation subsystem;receiving a first program content signal;determining a first spectral mismatch based at least upon a cross power spectral density of the first program content signal and the residual signal;receiving a second program content signal;determining a second spectral mismatch based at least upon a cross power spectral density of the second program content signal and the residual signal; andcontrolling a filter to filter the residual signal based upon the first spectral mismatch, the second spectral mismatch, a spectral density of the first program content signal, a spectral density of the second program content signal, and a spectral density of the residual signal.2. The method of wherein controlling the filter includes calculating filter coefficients and providing the filter coefficients to the filter.3. The method of wherein controlling the filter to filter the residual signal is based upon a previously determined first spectral mismatch and a previously determined second spectral mismatch during a period of time when a double-talk condition is detected.4. The method of further ...

Подробнее
Номер записи: 74
15-02-2018 дата публикации

SYSTEM AND METHOD FOR ADDRESSING ACOUSTIC SIGNAL REVERBERATION

Номер: US20180047408A1
Автор: Tebelmann Lars, Wolff Tobias
Принадлежит:

A method, computer program product, and computer system for addressing acoustic signal reverberation is provided. Embodiments may include receiving, at one or more microphones, a first audio signal and a reverberation audio signal. Embodiments may further include processing at least one of the first audio signal and the reverberation audio signal. Embodiments may also include limiting a model based reverberation equalizer using a temporal constraint for direct sound distortions, the model based reverberation equalizer configured to generate one or more outputs, based upon, at least in part, at least one of the first audio signal and the reverberation audio signal. 1. A computer-implemented method comprising:receiving, at one or more microphones, a first audio signal;receiving, at the one or more microphones, a reverberation audio signal;processing at least one of the first audio signal and the reverberation audio signal; andlimiting a model based reverberation equalizer using a temporal constraint for direct sound distortions, the model based reverberation equalizer configured to generate one or more outputs, based upon, at least in part, at least one of the first audio signal and the reverberation audio signal.2. The computer-implemented method of claim 1 , further comprising:receiving the one or more outputs from the model based reverberation equalizer at a postfilter.3. The computer-implemented method of claim 1 , further comprising:receiving a beamformer output at a postfilter.4. The computer-implemented method of claim 1 , further comprising:adjusting the model based reverberation equalizer to obtain a particular direct-to-noise ratio.5. The computer-implemented method of claim 4 , further comprising:measuring the direct-to-noise ratio using, at least in part, at least one temporal criteria.6. The computer-implemented method of claim 4 , further comprising:using the model based reverberation equalizer for the particular direct-to- noise ratio as a constraint ...

Подробнее
Номер записи: 75
18-02-2021 дата публикации

ECHO CANCELLATION METHOD AND APPARATUS BASED ON TIME DELAY ESTIMATION

Номер: US20210051404A1
Автор: HU Guoping, LI Mingzi, MA Feng, WANG Haikun, WANG ZHIGUO
Принадлежит: IFLYTEK CO., LTD.

An echo cancellation method based on delay estimation is provided. In the method, a microphone signal and a reference signal are received and preprocessed. In the preprocessed microphone signal and the preprocessed reference signal, frequency point signals with non-linearity in a current echo cancellation scenario are determined. A current delay estimation value is calculated based on frequency point signals without non-linearity in the microphone signal and the reference signal. The reference signal is shifted based on the current delay estimation value. An adaptive filter is updated based on the preprocessed microphone signal and the shifted reference signal, to perform echo cancellation. 1. An echo cancellation method based on delay estimation , comprising:receiving a microphone signal and a reference signal, and preprocessing the microphone signal and the reference signal;determining, in the preprocessed microphone signal and the preprocessed reference signal, frequency point signals with non-linearity in a current echo cancellation scenario;calculating a current delay estimation value based on frequency point signals without non-linearity in the microphone signal and the reference signal;shifting the reference signal based on the current delay estimation value; andupdating an adaptive filter based on the preprocessed microphone signal and the shifted reference signal, to perform echo cancellation.2. The method according to claim 1 , wherein the determining claim 1 , in the preprocessed microphone signal and the preprocessed reference signal claim 1 , frequency point signals with non-linearity in a current echo cancellation scenario comprises one or more of:a far-end signal detection, comprising determining the frequency point signals with non-linearity based on one or more of energy, a zero-crossing rate, and a short-term amplitude of the preprocessed reference signal;a dual-end signal detection, comprising determining the frequency point signals with non- ...

Подробнее
Номер записи: 76
06-02-2020 дата публикации

ACOUSTIC SIGNAL PROCESSING DEVICE, ACOUSTIC SIGNAL PROCESSING METHOD, AND HANDS-FREE COMMUNICATION DEVICE

Номер: US20200045166A1
Автор: Furuta Satoru
Принадлежит: Mitsubishi Electric Corporation

An acoustic signal processing device includes an acoustic signal analysis unit that analyzes an acoustic feature of a reception signal from a far end side and thereby generates an appropriate control signal, an echo canceller that cancels an acoustic echo mixed into an input acoustic signal, a noise canceller that cancels noise mixed into the input acoustic signal, and a speech enhancement unit that enhances a feature of speech included in the input acoustic signal, and thus high speech quality can be maintained irrespective of the type of a mobile phone or a communication network, and a high-quality hands-free voice call and high-accuracy speech recognition become possible. 1. An acoustic signal processing device comprising:a first storage unit storing first reference data;a second storage unit storing second reference data;an acoustic parameter calculation unit to analyze a first acoustic signal of reception voice inputted from a far end side and to generate an analytic acoustic parameter;an acoustic parameter analysis unit to analyze the analytic acoustic parameter by using the first reference data and thereby generate a parameter analysis result;a control signal generation unit to generate a control signal for correcting a second acoustic signal of transmission voice inputted from a near end side based on the parameter analysis result by using the second reference data; andan acoustic signal correction unit to make a correction of the second acoustic signal based on the control signal.2. The acoustic signal processing device according to claim 1 , wherein the acoustic signal correction unit includes an echo canceller that performs an echo cancellation process claim 1 , as the correction for removing an acoustic echo included in the second acoustic signal claim 1 , based on the control signal.3. The acoustic signal processing device according to claim 1 , wherein the acoustic signal correction unit includes a noise canceller that performs a noise cancellation ...

Подробнее
Номер записи: 77
13-02-2020 дата публикации

ELEVATOR COMMUNICATIONS SYSTEM

Номер: US20200048033A1
Автор: Pahlke Derk Oscar
Принадлежит:

An elevator system includes a hoistway; an elevator car configured to travel in the hoistway; a local gateway device configured to communicate with a remote system over a communications network; a communications apparatus installed at the elevator car, the communications apparatus including a codec configured to encode audio data from the elevator car prior to transmission to the local gateway device. 1. An elevator system comprising:a hoistway;an elevator car configured to travel in the hoistway;a local gateway device configured to communicate with a remote system over a communications network;a communications apparatus installed at the elevator car, the communications apparatus including a codec configured to encode audio data from the elevator car prior to transmission to the local gateway device.2. The elevator system of wherein the codec is configured to decode audio data received from the local gateway device.3. The elevator system of wherein the communications apparatus comprises and speaker and a microphone.4. The elevator system of wherein the communications apparatus comprises a plurality of microphones.5. The elevator system of wherein the communications apparatus performs echo cancelation on audio received from the plurality of microphones.6. The elevator system of wherein the communications apparatus comprises a communications module configured to send and receive encoded audio data to and from the local gateway device.7. The elevator system of wherein the communications module sends or receives the encoded audio data at a rate of about 0.5 kbps to about 10 kbps.8. A communications apparatus for an elevator system claim 6 , the communications apparatus comprising:a microphone;a speaker;a processor coupled to the microphone and speaker;a codec configured to (i) encode audio data received from the microphone for transmission to a local gateway device and (ii) decode encoded audio data received from the local gateway device for transmission to the speaker; ...

Подробнее
Номер записи: 78
03-03-2022 дата публикации

SIGNAL PROCESSING APPARATUS, SIGNAL PROCESSING METHOD, AND PROGRAM

Номер: US20220068288A1
Автор: KINOSHITA Keisuke, Nakatani Tomohiro
Принадлежит: Nippon Telegraph and Telephone Corporation

To sufficiently suppress noise and reverberation, a convolutional beamformer for calculating, at each time point, a weighted sum of a current signal and a past signal sequence having a predetermined delay and a length of 0 or more such that it increases a probability expressing a speech-likeness of an estimation signals based on a predetermined probability model is acquired where the estimation signals are acquired by applying the convolutional beamformer to frequency-divided observation signals corresponding respectively to a plurality of frequency bands of observation signals acquired by picking up acoustic signals emitted from a sound source, whereupon target signals are acquired by applying the acquired convolutional beamformer to the frequency-divided observation signals. 1. A signal processing device comprising processing circuitry configured to implement:an estimation unit that acquires a convolutional beamformer for calculating, at each time point, a weighted sum of a current signal and a past signal sequence having a predetermined delay and a length of 0 or more such that estimation signals increase a probability expressing a speech-likeness of the estimation signals based on a predetermined probability model where the estimation signals are acquired by applying the convolutional beamformer to frequency-divided observation signals corresponding respectively to a plurality of frequency bands of observation signals acquired by picking up acoustic signals emitted from a target sound source; anda suppression unit that acquires target signals by applying the convolutional beamformer acquired by the estimation unit to the frequency-divided observation signals.2. The signal processing device according to claim 1 , whereinthe estimation unit acquires the convolutional beamformer which maximizes the probability expressing the speech-likeness of the estimation signals based on the probability model.3. The signal processing device according to claim 1 , whereinthe ...

Подробнее
Номер записи: 79
03-03-2022 дата публикации

Speech Processing Method and System in A Cochlear Implant

Номер: US20220068289A1
Автор: Feng Qing Yang Zeng, Norden Eh Huang
Принадлежит: Aidiscitech Resarch Institute Co ltd

The invention discloses a speech processing method and system in a cochlear implant. The method includes: obtaining a sound signal, and converting the sound signal into a digital signal; decomposing the digital signal using a mode decomposition method, obtaining a plurality of intrinsic mode functions, and converting the plurality of intrinsic mode functions into instantaneous frequencies and instantaneous amplitudes or instantaneous energy intensities; sorting the instantaneous frequencies to corresponding the preset electrode frequency bands of the electrodes in the cochlear implant; selecting N most energetic components from the corresponding frequency bands of the electrodes, and generating corresponding electrode stimulation signals according to the selected components. The present invention analyzes sound and composes the final electrode signals all in the time domain based on Hilbert-Huang transform; it is not limited by the principle of uncertainty, and there is no noise generated by harmonics.

Подробнее
Номер записи: 80
25-02-2016 дата публикации

ACTIVE ACOUSTIC FILTER WITH SOCIALLY DETERMINED LOCATION-BASED FILTER CHARACTERISTICS

Номер: US20160055861A1
Автор: III Richard Fritz, Kraft Noah, Lanman, WIGGINS Dan
Принадлежит:

There is disclosed active acoustic filter systems and methods. A processor is disposed within a housing configured to interface with a user's ear. A memory stores data defining one or more locations and a respective set of location-based processing parameters associated with each of the one or more locations. A personal computing device external to the housing is coupled to the processor via a first wireless communications link. The personal computing device determines a current location of the active acoustic filter system. The processor generates digitized processed sound by processing digitized ambient sound in accordance with a set of location-based processing parameters retrieved from the memory, the retrieved set of location-based processing parameters associated with the current location of the active acoustic filter system as determined by the personal computing device. 1. An active acoustic filter system , comprising:a housing configured to interface with a user's ear;an input subsystem disposed within the housing and comprising a microphone, a preamplifier and an analog to digital converter coupled to one another, the input subsystem configured to convert ambient sound into digitized ambient sound;a memory storing data defining one or more locations and a respective set of location-based processing parameters corresponding with each of the one or more locations;a geolocation engine configured to determine a current location of the active acoustic filter system;a processor disposed within the housing and coupled to the input subsystem, wherein the processor generates digitized processed sound by processing the digitized ambient sound in accordance with the set of location-based processing parameters stored in the memory which corresponds to the determined location of the active acoustic filter system provided by the geolocation engine; andan output subsystem disposed within the housing and coupled to the processor, the output subsystem comprising a digital ...

Подробнее
Номер записи: 81
25-02-2016 дата публикации

SYSTEM AND METHOD FOR ADDRESSING ACOUSTIC SIGNAL REVERBERATION

Номер: US20160055862A1
Автор: Tebelmann Lars, Wolff Tobas
Принадлежит:

A system and method for addressing acoustic signal reverberation is provided. Embodiments may include receiving, at one or more microphones, a first audio signal and a reverberation audio signal. Embodiments may further include processing at least one of the first audio signal and the reverberation audio signal. Embodiments may also include limiting a model based reverberation equalizer using a temporal constraint for direct sound distortions, the model based reverberation equalizer configured to generate one or more outputs, based upon, at least in part, at signal least one of the first audio signal and the reverberation audio signal. 1. A computer-implemented method comprising:receiving, at one or more microphones, a first audio signal;receiving, at the one or more microphones, a reverberation audio signal;processing at least one of the first audio signal and the reverberation audio signal; andlimiting a model based reverberation equalizer using a temporal constraint for direct sound distortions, the model based reverberation equalizer configured to generate one or more outputs, based upon, at least in part, at least one of the first audio signal and the reverberation audio signal.2. The computer-implemented method of claim 1 , further comprising:receiving the one or more outputs from the model based reverberation equalizer at a postfilter.3. The computer-implemented method of claim 1 , further comprising:receiving a beamformer output at a postfilter.4. The computer-implemented method of claim 1 , further comprising:adjusting the model based reverberation equalizer to obtain a particular direct-to-noise ratio.5. The computer-implemented method of claim 4 , further comprising:measuring the direct-to-noise ratio using, at least in part, at least one temporal criteria.6. The computer-implemented method of claim 4 , further comprising:using the model based reverberation equalizer for the particular direct-to-noise ratio as a constraint equalizer configured to limit ...

Подробнее
Номер записи: 82
14-02-2019 дата публикации

Voice assistant system, server apparatus, device, voice assistant method therefor, and program to be executed by copmuter

Номер: US20190051289A1
Автор: Kazuhiro Kosugi, Koji Kawakita, Masaharu Yoneda
Принадлежит: Lenovo Singapore Pte Ltd

A voice assistant system includes a server apparatus performing voice assistant and a plurality of devices, in which the server apparatus and the devices are communicatively connected to each other. The plurality of devices each records the same user's speech through a microphone, and then transmits recorded data of the same user's speech to the server apparatus. The server apparatus receives the recorded data transmitted from each of the plurality of devices, and then voice-recognizes two or more of the received recorded data in accordance with a predetermined standard to thereby interpret the contents of the user's speech to perform the voice assistant.

Подробнее
Номер записи: 83
14-02-2019 дата публикации

LOUDSPEAKER SYSTEM

Номер: US20190051300A1
Автор: Liao Cheng Yang
Принадлежит:

A loudspeaker system includes a host processor, a audio output unit, a motion detection module and a voice control module. The host processor is electrically connected to the audio output unit, the motion detection module and the voice control module, respectively. The motion detection module detects a motion of a user. The host processor controls an output signal of the audio output unit according to the detected motion and the voice control module receives a voice command, to enable the host processor to control an operation. 1. A loudspeaker system , comprising:a host processor;an audio output unit, electrically connected to the host processor;a motion detection module, electrically connected to the host processor and configured to detect a motion of a user; anda voice control module, electrically connected to the host processor,wherein the host processor is configured to control an output signal of the audio output unit according to the motion detected by the motion detection module, and the voice control module is configured to receive a voice command enabling the host processor to control an operation of the loudspeaker system.2. The loudspeaker system according to claim 1 , further comprising a main body claim 1 ,wherein the host processor, the audio output unit, and the voice control module are disposed within the main body, and the motion detection module is a standalone unit outside of the main body.3. The loudspeaker system according to claim 1 , wherein the host processor is configured to control the output signal of the audio output unit to lower a volume of the loudspeaker system claim 1 , the audio output unit is electrically connected to the voice control module claim 1 , and the voice control module is configured to implement automatic echo cancellation.4. A loudspeaker system claim 1 , comprising: a first processor; and', 'a first transceiver electrically connected to the first processor; and, 'a first speaker apparatus, comprising a second ...

Подробнее
Номер записи: 84
14-02-2019 дата публикации

Automated clinical documentation system and method

Номер: US20190051377A1
Автор: Daniel Paulino ALMENDRO BARREDA, Donald E. Owen, Dushyant Sharma
Принадлежит: Nuance Communications Inc

A mixed-media ACD device is configured to monitor one or more encounter participants of a patient encounter and includes a machine vision system configured to obtain machine vision encounter information concerning the patient encounter. An audio recording system is configured to obtain audio encounter information concerning the patient encounter, wherein the audio recording system includes a plurality of discrete audio acquisition devices.

Подробнее
Номер записи: 85
14-02-2019 дата публикации

Automated Clinical Documentation System and Method

Номер: US20190051378A1
Автор: Almendro Barreda Daniel Paulino, Gallopyn Guido Remi Marcel, Jost Uwe Helmut, Naylor Patrick, Nour-Eldin Amr, Owen Donald E., Sharma Dushyant
Принадлежит:

A method, computer program product, and computing system for source separation is executed on a computing device and includes obtaining encounter information of a patient encounter, wherein the encounter information includes first audio encounter information obtained from a first encounter participant and at least a second audio encounter information obtained from at least a second encounter participant. The first audio encounter information and the at least a second audio encounter information are processed to eliminate audio interference between the first audio encounter information and the at least a second audio encounter information. 1. A computer-implemented method for source separation , executed on a computing device , comprising:obtaining encounter information of a patient encounter, wherein the encounter information includes first audio encounter information obtained from a first encounter participant and at least a second audio encounter information obtained from at least a second encounter participant; andprocessing the first audio encounter information and the at least a second audio encounter information to eliminate audio interference between the first audio encounter information and the at least a second audio encounter information.2. The computer-implemented method of wherein obtaining encounter information of a patient encounter includes:steering a first audio recording beam toward the first encounter participant; andsteering at least a second audio recording beam toward the at least a second encounter participant.3. The computer-implemented method of wherein processing the first audio encounter information and the at least a second audio encounter information to eliminate audio interference includes:executing an echo cancellation process on the first audio encounter information and the at least a second audio encounter information.4. The computer-implemented method of wherein processing the first audio encounter information and the at least a ...

Подробнее
Номер записи: 86
14-02-2019 дата публикации

Automated clinical documentation system and method

Номер: US20190051381A1
Автор: Donald E. Owen
Принадлежит: Nuance Communications Inc

A method, computer program product, and computing system for proactive encounter scanning is executed on a computing device and includes obtaining encounter information of a patient encounter. The encounter information is proactively processed to determine if the encounter information is indicative of one or more medical conditions and to generate one or more result set. The one or more result sets are provided to the user.

Подробнее
Номер записи: 87
14-02-2019 дата публикации

Automated clinical documentation system and method

Номер: US20190051384A1
Автор: Daniel Paulino ALMENDRO BARREDA, Dushyant Sharma, Guido Remi Marcel Gallopyn, Patrick A. NAYLOR
Принадлежит: Nuance Communications Inc

A method, computer program product, and computing system for monitoring a plurality of encounter participants is executed on a computing device and includes obtaining encounter information of a patient encounter. The encounter information is processed to: associate at least a first portion of the encounter information with at least one known encounter participant, and associate at least a second portion of the encounter information with at least one unknown encounter participant.

Подробнее
Номер записи: 88
14-02-2019 дата публикации

Automated Clinical Documentation System and Method

Номер: US20190051386A1
Автор: Donald E. Owen, Garret N. Erskine, Mehmet Mert Öz
Принадлежит: Nuance Communications Inc

A method, computer program product, and computing system for automating an intake process is executed on a computing device and includes prompting a patient to provide encounter information via a virtual assistant during a pre-visit portion of a patient encounter. Encounter information is obtained from the patient in response to the prompting by the virtual assistant.

Подробнее
Номер записи: 89
25-02-2021 дата публикации

USING STRUCTURED AUDIO OUTPUT TO DETECT PLAYBACK AND/OR TO ADAPT TO MISALIGNED PLAYBACK IN WIRELESS SPEAKERS

Номер: US20210056964A1
Автор: Cao Xiang, NESIBA Nathaniel
Принадлежит:

Implementations are directed to determining an audio delay, of a computing device, by causing an audio data stream to be transmitted to the computing device via a wireless communication channel. The computing device causes audio output generated using the audio data stream to be rendered via speaker(s). The rendered audio output is captured via microphone(s), and the audio delay determined by comparing the captured audio output with the audio data stream. A delay audio segment can be appended to an additional audio data stream transmitted to the computing device, where the length of the delay audio segment is determined using the audio delay. A noise reduction technique can additionally or alternatively be adapted based on the audio delay. Implementations are additionally or alternatively directed to determining if an audio data stream transmitted to a computing device for rendering through speaker(s) driven by the computing device—is actually being rendered. 1. A method implemented by one or more processors , the method comprising: wherein transmitting the audio data stream causes the vehicle computing device to render audible output via one or more vehicle speakers of the vehicle, and', 'wherein the audible output is generated by the vehicle computing device based on at least part of the audio data stream;, 'causing a computing device to transmit, via a wireless communication channel, an audio data stream to a vehicle computing device of a vehicle,'}receiving captured audio data that is captured by at least one microphone within the vehicle, wherein the captured audio data captures the audible output rendered by the at least one vehicle speaker;determining a vehicle audio delay based on comparing the captured audio data to the audio data stream; and 'causing the computing device to append a corresponding delay audio segment to an additional audio data stream prior to transmitting the additional audio data stream to the vehicle computing device via the wireless ...

Подробнее
Номер записи: 90
22-02-2018 дата публикации

REVERBERATION COMPENSATION FOR FAR-FIELD SPEAKER RECOGNITION

Номер: US20180053512A1
Автор: Biswal Narayan, Cilingir Gokcen
Принадлежит: Intel Corporation

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. A processor-implemented method for speaker recognition , the method comprising:receiving, by a processor, an authentication audio signal associated with speech of a user;extracting, by the processor, features from the authentication audio signal;scoring, by the processor, results of application of one or more speaker models to the extracted features, wherein each of the speaker models is trained based on a training audio signal, the training audio signal processed by a reverberation simulator to simulate selected far-field environmental effects to be associated with the speaker model;selecting, by the processor, one of the speaker models based on the score; andmapping, by the processor, the selected speaker model to a known speaker identification (ID) associated with the user.2. The method of claim 1 , wherein the training of the speaker models further comprises:capturing a plurality of the training audio signals from a plurality of users;receiving a known speaker ID for each of the users; andprocessing each of the plurality of training audio signals by the reverberation simulator to generate a plurality of reverberation processed training audio signals ...

Подробнее
Номер записи: 91
22-02-2018 дата публикации

Method and apparatus to improve speech recognition in a high audio noise environment

Номер: US20180053518A1
Автор: Eric CHRISMAN
Принадлежит: Vocollect Inc

A method improves speech recognition using a device located in proximity to a machine emitting high levels of audio noise. The microphone of the device receives the audio noise emitted by the machine and the speech emitted by a user and generates a composite signal. The device also receives a wireless communication signal from the machine comprising information on an audio noise profile and the proximity of the machine relative to the device. The audio noise profile is a representation of the audio noise emitted by the machine. Based on this information, the device determines a filter for filtering the composite signal to mitigate the audio noise before initiating the speech recognition process. The method improves speech recognition in a high audio noise environment.

Подробнее
Номер записи: 92
13-02-2020 дата публикации

APPARATUS AND METHOD FOR MULTICHANNEL INTERFERENCE CANCELLATION

Номер: US20200051581A1
Автор: ANNIBALE Paolo, HABETS Emanuel, LOMBARD Anthony, LUIS VALERO Maria, RUTHA Marcel, WILD Moritz
Принадлежит:

An apparatus for multichannel interference cancellation in a received audio signal including two or more received audio channels to obtain a modified audio signal including two or more modified audio channels is provided. The apparatus includes a first filter unit being configured to generate a first estimation of a first interference signal depending on a reference signal. Moreover, the apparatus includes a first interference canceller being configured to generate a first modified audio channel of the two or more modified audio channels from a first received audio channel of the two or more received audio channels depending on the first estimation of the first interference signal. Furthermore, the apparatus includes a second filter unit being configured to generate a second estimation of a second interference signal depending on the first estimation of the first interference signal. 1. An apparatus for multichannel interference cancellation in a received audio signal comprising two or more received audio channels to acquire a modified audio signal comprising two or more modified audio channels , wherein the apparatus comprises:a first filter unit being configured to generate a first estimation of a first interference signal depending on a reference signal,a first interference canceller being configured to generate a first modified audio channel of the two or more modified audio channels from a first received audio channel of the two or more received audio channels depending on the first estimation of the first interference signal,a second filter unit being configured to generate a second estimation of a second interference signal depending on the first estimation of the first interference signal, anda second interference canceller being configured to generate a second modified audio channel of the two or more modified audio channels from a second received audio channel of the two or more received audio channels depending on the second estimation of the second ...

Подробнее
Номер записи: 93
14-02-2019 дата публикации

AUDIO SIGNAL PROCESSING

Номер: US20190052959A1
Автор: JANSE Cornelis Pieter, VAN STUIVENBERG Leonardus Cornelis Antonius
Принадлежит:

An audio signal processing apparatus comprises a receiver () receiving an audio signal sampled at a first sampling frequency, the audio signal having a maximum frequency below half the first sampling frequency by a first frequency margin. A tilter bank () generates subband signals for the digital audio signal using overlapping sub-filters. A first frequency shifter () applies a frequency shift to at least one subband of the set of subbands and a decimator () decimates the subband signals by a N decimation factor resulting in a decimated sampling frequency being at least twice a bandwidth of each of the overlapping sub-filters. The frequency shift for a subband is arranged to shift the subband to a frequency interval being a multiple of a frequency interval from zero to half the decimated sample frequency. The subband may be individually processed and the processed subbands may subsequently be combined to generate a full band output signal. 2. The audio signal processing apparatus of further comprising a signal processor arranged to apply a signal processing algorithm to the audio signal by applying separate subband signal processing in each subband.3. The audio signal processing apparatus of wherein the signal processing algorithm is a speech processing algorithm claim 2 , and the signal processor is arranged to apply different algorithms in different subbands.4. The audio signal processing apparatus of wherein the signal processing algorithm comprises applying an adaptive filter claim 2 , and the signal processor is arranged to adapt the adaptive filter separately in different subbands.5. The audio signal processing apparatus of wherein the audio signal and the adaptive filter is an echo cancellation filter for estimating an echo of the audio signal claim 4 , the echo cancellation filter comprising a sub-echo cancellation filter for each subband; and the signal processor is arranged to:determine estimated echo signals for each subband by applying a sub-echo ...

Подробнее
Номер записи: 94
25-02-2021 дата публикации

ARRAY MICROPHONE AND SOUND COLLECTION METHOD

Номер: US20210058700A1
Автор: IKEGAYA Yuji, Yamakawa Takashi
Принадлежит:

A sound collection method and a microphone array estimate at least one sound source direction and form a plurality of sound collection beams in the estimated plurality of sound source direction, using sound collection signals of a plurality of microphones. The number of sound source directions estimated is smaller than the number of sound collection beams formed. 1. A microphone array comprising:a plurality of microphones;an estimator that estimates at least one sound source direction;a beam former that forms, using sound collection signals from the plurality of microphones, a plurality of sound collection beams larger in number than the number of the estimated at least one sound source direction but no more than a predetermined maximum number;a memory storing information indicating a beam direction of each of the plurality of sound collection beams;a determiner that determines whether or not a number of the plurality of sound collection beams reaches the predetermined maximum number; andan updater that updates at least one of the stored beam directions to the estimated at least one sound source direction upon the number of the plurality of sound collection beams being determined to reach the predetermined maximum number.2. The microphone array according to claim 1 , further comprising a mixing processor that mixes an audio signal corresponding to one sound collection beam claim 1 , among the plurality of sound collection beams claim 1 , by a gain according to volume of the one sound collection beam.3. The microphone array according to claim 1 , wherein the updater updates the direction of an earliest updated sound collection beam among the plurality of sound collection beams.4. The microphone array according to claim 1 , wherein the plurality of microphones are configured as a ceiling tile.5. The microphone array according to claim 1 , wherein the updater updates the direction of a sound collection beam with the direction thereof closest to the estimated at least ...

Подробнее
Номер записи: 95
13-02-2020 дата публикации

METHOD FOR IMPROVING ECHO CANCELLATION EFFECT AND SYSTEM THEREOF

Номер: US20200053224A1
Автор: Zhang Henglizi
Принадлежит:

A method for improving an echo cancellation effect and a system thereof are disclosed. The method comprises includes: performing a non-linear compensation for a non-linear response portion of an excitation signal using an NLC algorithm to obtain a compensated excitation signal; outputting the compensated excitation signal to an echo cancellation system; and performing echo cancellation for the compensated excitation signal by the echo cancellation system. According to the present disclosure, using the NLC algorithm, non-linear compensation is performed for the non-linear portion of the excitation signal, non-linear outputs generated due to non-linear characteristics of the system are pre-compensated when being input to the echo cancellation system, such that the echo signal output by the echo cancellation system is minimized and the echo cancellation effect is improved. 1. A method for improving echo cancellation effect , which comprising the following steps of:Step S1, performing a non-linear compensation for a non-linear response portion of an excitation signal using an NLC algorithm to obtain a compensated excitation signal;Step S2, outputting the compensated excitation signal to the an echo cancellation system; andStep S3, performing echo cancellation for the compensated excitation signal by the echo cancellation system.2. The method according to claim 1 , wherein the compensated excitation signal comprises a linear response portion and a background noise portion of the excitation signal.3. The method according to claim 2 , wherein the non-linear response portion of the excitation signal is converted to at least one of a linear response portion or a smaller non-linear response portion upon the non-linear compensation.4. An echo cancellation system claim 2 , comprising:a non-linear compensation module; andan echo cancellation device;wherein the non-linear compensation module is configured to perform a non-linear compensation for an excitation signal using an NLC ...

Подробнее
Номер записи: 96
10-03-2022 дата публикации

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

Номер: US20220076684A1
Автор: YANG XIN
Принадлежит:

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 ...

Подробнее
Номер записи: 97
10-03-2022 дата публикации

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

Номер: US20220076686A1
Автор: Madhusudhan Seetharam, Rajendran Pichaimurthy
Принадлежит: Rovi Guides Inc

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.

Подробнее
Номер записи: 98
10-03-2022 дата публикации

METHOD AND APPARATUS FOR OPTIMIZING SOUND QUALITY FOR INSTANT MESSAGING

Номер: US20220076688A1
Автор: DONG Pei, GUO LIANG, Zhang Chen
Принадлежит:

Disclosed are an instant messaging sound quality optimization method, an apparatus and a device. The method includes: obtaining first human voice data, the first human voice data being voice data of a user of a first client terminal; using a loudspeaker to play the first human voice data, local background music of a second client terminal to obtain first audio data; using a microphone to collect the first audio data and second human voice data to obtain second audio data, the second human voice data being voice data of a user of a second client terminal; filtering the first human voice data in the second audio data to obtain filtered audio data; when the background music played by the first client terminal is the second client terminal, sending the filtered audio data to the first client terminal to enable the first client terminal to play the filtered audio data. 1. A method for optimizing sound quality for instant messaging , applied to a second client and comprising:obtaining a first human voice data, wherein the first human voice data are voice data of a user of a first client;obtaining a first audio data by playing the first human voice data and a local background music of the second client through one or more speakers;obtaining a second audio data by collecting the first audio data and a second human voice data through one or more microphones, wherein the second human voice data is voice data of a user of the second client;filtering the first human voice data in the second audio data to obtain a filtered audio data; andsending the filtered audio data to the first client in response to a background music played by the first client coming from the second client to make the first client play the filtered audio data.2. The method according to claim 1 , wherein said obtaining the first human voice data comprises:receiving the first human voice data sent by the first client in response to the first client playing the background music with earphones; orreceiving the ...

Подробнее
Номер записи: 99
10-03-2022 дата публикации

SYSTEMS AND METHODS FOR FILTERING UNWANTED SOUNDS FROM A CONFERENCE CALL

Номер: US20220076689A1
Автор: Pichaimurthy Rajendran, Seetharam Madhusudhan
Принадлежит:

To filter unwanted sounds from a conference call, a voice profile of a first user is generated based on a first voice signal captured by a media device during a first conference call. The voice profile may be generated by identifying a base frequency of the first voice signal and determining a plurality of voice characteristics, such as pitch, intonation, accent, loudness, and speech rate. These data may be stored in association with the first user. During a second conference call, a second voice signal captured by the media device is analyzed to determine, based on the voice profile of the first user, whether the second voice signal includes the voice of a second user. If so, the second voice signal is prevented from being transmitted into the conference call. A voice profile of the second user may be generated from the second voice signal for future use. 1. A method for filtering unwanted sounds from a conference call , the method comprising:generating a voice profile of a first user of a media device based on a first voice signal captured by the media device during a first conference call; and analyzing a second voice signal captured by the media device during the second conference call;', 'determining, using the voice profile of the first user, that the second voice signal includes a voice of a second user different from the first user; and', 'in response to determining that the second voice signal includes a voice of a second user, preventing the second voice signal from being transmitted into the second conference call., 'during a second conference call2. The method of claim 1 , further comprising generating a second voice profile of the second user based on the second voice signal captured by the media device.3. The method of claim 1 , wherein the second voice signal is captured using a microphone claim 1 , and wherein preventing the second voice signal from being transmitted into the second conference call comprises muting the microphone for a predetermined ...

Подробнее
Номер записи: 100