УЛУЧШЕНИЕ РАЗБОРЧИВОСТИ РЕЧИ В МОБИЛЬНОМ КОММУНИКАЦИОННОМ УСТРОЙСТВЕ ПУТЕМ УПРАВЛЕНИЯ РАБОТОЙ ВИБРАТОРА В ЗАВИСИМОСТИ ОТ ФОНОВОГО ШУМА

Изобретение относится к мобильным коммуникационным устройствам, в частности, имеющим средства для улучшения разборчивости выводимых ими аудиосигналов в присутствии внешнего шума. Техническим результатом является создание мобильного коммуникационного устройства, улучшающего разборчивость речи при разных уровнях фонового шума. Указанный технический результат достигается тем, что мобильное коммуникационное устройство содержит громкоговоритель (14) для воспроизведения речи из речевого сигнала (s(n)), вибратор (22), средство (24) для измерения фонового шума относительно воспроизводимой речи и блок (16) управления вибратором для генерирования управляющего сигнала в зависимости от фонового шума для управления работой вибратора (22) во время воспроизведения речи в зависимости от уровня фонового шума. 2 н. и 6 з.п. ф-лы, 6 ил.

ПОВЫШЕНИЕ РАЗБОРЧИВОСТИ РЕЧИ В ЗВУКОЗАПИСИ РАЗВЛЕКАТЕЛЬНЫХ ПРОГРАММ

Изобретение относится к обработке сигналов звукозаписи, в частности к повышению разборчивости звукозаписи развлекательных программ, таких как телевизионная звукозапись. Техническим результатом является улучшение ясности и разборчивости речи, такой как звукозапись диалогов и повествовательного изложения. Указанный результат достигается тем, что в ответ на одно или более управляющих воздействий обрабатывают звукозапись развлекательных программ: изменяют уровень сигнала звукозаписи в каждой из множества полос частот в соответствии с характеристикой коэффициента усиления, которая соотносит уровень сигнала полосы с коэффициентом усиления. Далее формируют управляющий сигнал для изменения характеристики коэффициента усиления в каждой полосе частот: определяют в одной широкой полосе частот отрезки времени звукозаписи развлекательных программ (а) как речевые или неречевые либо (b) как вероятно являющиеся речевыми или неречевыми, получают в каждой из множества полос частот величину пульсаций уровней ...

УСТРОЙСТВО И СПОСОБ ДЛЯ ГЕНЕРАЦИИ МНОГОКАНАЛЬНОГО СИГНАЛА, ИСПОЛЬЗУЮЩИЕ ОБРАБОТКУ ГОЛОСОВОГО СИГНАЛА

Изобретение относится к обработке звукового сигнала, в частности к производству нескольких выходных каналов из меньшего количества входных каналов, например, из одного (моно) канала или двух (стерео) входных каналов. Техническим результатом является повышение качества производства многоканального сигнала, включающего ряд выходных каналов. Указанный результат достигается тем, что устройство для генерирования многоканального сигнала (10), включающего число выходных каналов большее, чем число входных каналов, используется микшер для повышающего микширования входного сигнала, чтобы сформировать сигнал прямого канала и сигнал канала окружения. Речевой детектор (18) предоставлен для того, чтобы обнаружить часть входного сигнала, сигнала прямого канала или сигнала канала окружения, в котором встречаются речевые части. Основанный на этом обнаружении модификатор сигнала (20) изменяет входной сигнал или сигнал канала окружения, чтобы ослабить речевые части в сигнале канала окружения, тогда как такие ...

Устройство и способ повышения разборчивости речи для респираторной маски

В настоящем документе описано устройство повышения разборчивости речи и респираторные маски, содержащие устройство повышения разборчивости речи, а также способы повышения разборчивости передачи речи для пользователя респираторной маски. В одном или более воплощениях устройство и способы повышения разборчивости речи, описываемые в настоящем документе, обнаруживают акустическую энергию в пределах первого диапазона частот внутри чистого воздушного пространства респираторной маски и доставляют компенсирующую акустическую энергию наружу из этого чистого воздушного пространства с использованием динамика. В одном или более воплощениях указанная компенсирующая акустическая энергия обладает таким предварительно определенным профилем ослабления амплитуды, что компенсирующая акустическая энергия имеет амплитуду менее чем на 6 дБ больше, чем указанный профиль акустического ослабления корпуса маски по меньшей мере в 90% предварительно определенного диапазона ослабляемых частот. 2 н. и 21 з.п. ф-лы, ...

КОНТРОЛЛЕР ВЫРАВНИВАТЕЛЯ ГРОМКОСТИ И СПОСОБ УПРАВЛЕНИЯ

Настоящее изобретение в целом относится к обработке звуковых сигналов. Описаны контроллер выравнивателя громкости и способ управления. В одном варианте осуществления контроллер выравнивателя громкости содержит классификатор звукового содержимого для идентификации типа содержимого звукового сигнала в реальном времени и регулирующий блок для регулировки выравнивателя громкости в непрерывном режиме в зависимости от идентифицированного типа содержимого. Регулирующий блок может выполняться с возможностью положительной корреляции коэффициента динамического усиления выравнивателя громкости с типами информативного содержимого звукового сигнала и отрицательной корреляции коэффициента динамического усиления выравнивателя громкости с типами мешающего содержимого звукового сигнала. Изобретение направлено на обеспечение возможности автоматически настраивать устройства улучшения качества звука в непрерывном режиме в зависимости от воспроизводимого звукового содержимого. 3 н. и 8 з.п. ф-лы, 41 ил., 2 ...

ПОВЫШЕНИЕ РАЗБОРЧИВОСТИ РЕЧИ В ЗВУКОЗАПИСИ РАЗВЛЕКАТЕЛЬНЫХ ПРОГРАММ

... 1. Способ повышения разборчивости речи в звукозаписи развлекательных программ, содержащий этапы, на которых ! обрабатывают в ответ на одно или более управляющих воздействий звукозапись развлекательных программ для улучшения ясности и разборчивости участков речи в звукозаписи развлекательных программ, при этом обработка включает в себя этапы, на которых ! изменяют уровень звукозаписи развлекательных программ в каждой из множества полос частот в соответствии с характеристикой коэффициента усиления, которая соотносит уровень сигнала полосы с коэффициентом усиления, и ! формируют управляющий сигнал для изменения характеристики коэффициента усиления в каждой полосе частот, при этом формирование включает в себя этапы, на которых ! характеризуют отрезки времени звукозаписи развлекательных программ (a) как речевые или неречевые, либо (b) как вероятно являющиеся речевыми или неречевыми, при этом определение производится в одной широкой полосе частот, ! получают в каждой из упомянутого множества ...

ОПТИМИЗАЦИЯ ГРОМКОСТИ И ДИНАМИЧЕСКОГО ДИАПАЗОНА ЧЕРЕЗ РАЗЛИЧНЫЕ УСТРОЙСТВА ВОСПРОИЗВЕДЕНИЯ

СПОСОБ ПОВЫШЕНИЯ РАЗБОРЧИВОСТИ РЕЧИ ПОЖИЛЫМИ ЛЮДЬМИ ПРИ ПРИЕМЕ ЗВУКОВЫХ ПРОГРАММ НА НАУШНИКИ

Изобретение относится к средствам для повышения разборчивости речи пожилыми людьми при приеме звуковых программ на наушники. Технический результат заключается в повышении эффективности повышения разборчивости речи пожилыми людьми. Используют усилитель наушников с частотной характеристикой, обратной аудиограмме пожилого человека соответствующей возрастной группы. Возможное некоторое несоответствие параметров аудиограммы выбранной возрастной группы особенностям восприятия звуков конкретным человеком не препятствует повышению разборчивости речи. 1 ил.

РАСШИРЕНИЕ ПОЛОСЫ ЧАСТОТ ГАРМОНИЧЕСКОГО АУДИОСИГНАЛА

Изобретение относится к средствам для расширения полосы частот гармонического аудиосигнала. Технический результат заключается в повышении эффективности обработки аудиосигнала. Принимают через схему передачи данных гармонический аудиосигнал и множество значений усиления, ассоциированных с частотной полосой b, и количество соседних частотных полос для полосы b. Определяют с помощью аудиодекодера преобразования содержит ли по меньшей мере один спектральный пик реконструированная соответствующая полоса b’ частот в области расширенной полосы частот гармонического аудиосигнала. Когда реконструированная полоса b’ частот содержит спектральный пик: устанавливают с помощью аудиодекодера преобразования значение усиления, ассоциированное с реконструированной полосой частот b’ в первое значение на основе принятого множества значений усиления; в котором первое значение представляет собой взвешенную сумму принятого множества значений усиления. Когда реконструированная полоса b’ частот не содержит никакой ...

АУДИОКОДИРОВЩИК И ДЕКОДЕР

ОПТИМИЗАЦИЯ ГРОМКОСТИ И ДИНАМИЧЕСКОГО ДИАПАЗОНА ЧЕРЕЗ РАЗЛИЧНЫЕ УСТРОЙСТВА ВОСПРОИЗВЕДЕНИЯ

УЛУЧШЕНИЕ РАЗБОРЧИВОСТИ РЕЧИ В МОБИЛЬНОМ КОММУНИКАЦИОННОМ УСТРОЙСТВЕ ПУТЕМ УПРАВЛЕНИЯ РАБОТОЙ ВИБРАТОРА В ЗАВИСИМОСТИ ОТ ФОНОВОГО ШУМА

... 1. Мобильное коммуникационное устройство, содержащее ! громкоговоритель (14) для воспроизведения речи из речевого сигнала (s(n)), ! вибратор (22), ! средство (24) для измерения фонового шума относительно воспроизводимой речи и ! блок (16) управления вибратором для генерирования управляющего сигнала в зависимости от фонового шума для управления работой вибратора (22) во время воспроизведения речи в зависимости от уровня фонового шума. ! 2. Устройство по п.1, содержащее средство (30) для расчета сигнала спектра (|N(f)|) фонового шума, представляющего уровень фонового шума, при этом блок (16) управления вибратором выполнен с возможностью генерировать управляющий сигнал для выборочного включения вибратора (22) во время воспроизведения речи на основе сигнала спектра фонового шума. ! 3. Устройство по п.2, в котором средство (24) для измерения фонового шума содержит один или более микрофонов, при этом сигнал спектра (|N(f)|) фонового шума генерируется на основе вклада окружающего шума в один или ...

АУДИОКОДЕР И СПОСОБ ДЛЯ КОДИРОВАНИЯ АУДИОСИГНАЛА

System zur angepassten Reduktion von Geräuschen bei Sprachsignalen

Global optimierte Nachfilterung mit der Kleinste-Quadrate-Methode für die Sprachverbesserung

Bestehende Nachfilterverfahren zur Sprachverbesserung bei Mikrofonarrays haben zwei allgemeine Mängel. Zunächst gehen sie davon aus, dass Rauschen entweder diffus oder weiß ist, mit Punkstörern können sie nicht umgehen. Weiterhin ermitteln sie die Nachfilter-Koeffizienten für jeweils nur zwei Mikrofone und führen die Mittelwertbildung anhand der Mikrofonpaare durch, was keine optimale Lösung ergibt. Das bereitgestellte Verfahren beschreibt eine Nachfilterlösung, die Signalmodelle einführt, die weißes und diffuses Rauschen, sowie Punktstörer handhaben können. Das Verfahren implementiert auch einen global optimierten KQ-Ansatz für Mikrofone in einem Mikrofonarray und liefert dadurch im Vergleich zu herkömmlichen Verfahren eine optimalere Lösung. Die Ergebnisse der Experimente zeigen, wie das beschriebene Verfahren die herkömmlichen Methoden in verschiedenen akustischen Situationen leistungsmäßig übertrifft.

VORRICHTUNG UND VERFAHREN ZUR VERBESSERUNG DER PRIVATSPHÄRE

Ausführungsformen der vorliegenden Erfindung stellen ein Fahrzeug-Datenschutzsystem (700) dar, das Audioeingabemittel (130, 190, 720) zum Empfangen eines externen Audiosignals (725), das Audio von innerhalb eines Fahrzeugs (900) anzeigt, Audioquellenmittel (710) umfasst, 910) zum Empfangen des externen Audiosignals (725) und zum Bestimmen eines Ausgangsaudiosignals (735) in Abhängigkeit davon zum Reduzieren einer externen Sprachverständlichkeit innerhalb des Fahrzeugs (900), und Audioausgabemittel (145, 146, 147, 730, 920) zum Empfangen des Ausgangsaudiosignals (735) und zum Ausgeben von diesem entsprechendem Audio (925), um außerhalb des Fahrzeugs (900) zumindest teilweise hörbar zu sein.

VORRICHTUNG UND VERFAHREN ZUM ERZEUGEN EINES MULTIKANALSIGNALS MIT EINER SPRACHSIGNALVERARBEITUNG

Verfahren zur Verbesserung der Sprachverständlichkeit mit einem Hörhilfegerät sowie Hörhilfegerät

Hörhilfegerät (1; 11), umfassend wenigstens einen Eingangswandler (3, 4; M) zur Aufnahme eines Eingangssignals und Wandlung in ein elektrisches Eingangssignal (ES), eine Signalverarbeitungseinheit (5; SV1, SV2) zur Verarbeitung und frequenzabhängigen Verstärkung des elektrischen Eingangssignals (ES) und zur Erzeugung eines elektrischen Ausgangssignals (AS) und einen Ausgangswandler (6; R) zur Wandlung des elektrischen Ausgangssignals (AS) in ein von einem Benutzer als akustisches Ausgangssignal wahrnehmbares Ausgangssignal, Mittel zur Durchführung einer Frequenztransposition und zum Erzeugen eines transponierten Signals, Mittel zum Erfassen spezifischer Merkmale des elektrischen Eingangssignals, gekennzeichnet durch Filtermittel zum Filtern des transponierten Signals, wobei die Filterung in Abhängigkeit der erfassten spezifischen Merkmale des elektrischen Eingangssignals erfolgt.

Speech data processing method

The speech data processing method converts speech signals from a speaker into speech data which is processed via a processing device, in accordance with the hearing characteristics of the speaker, before delivery to an output or a storage location. The speech data processing may be interactive or effected according to a defined algorithm.

CODEBUCHSTRUKTUR UND SUCHVERFAHREN FÜR DIE SPRACHKODIERUNG

Verfahren zur adaptiven Filterung

Method and apparatus for speech enhancement in a speech communication system

A speech processing system and a speech processing method

Audio signal processing

Method and apparatus for speech enhancement in a speech communication system

A speech processing system and speech processing method

Improving speech intelligibility in presence of noise

A speech communication system comprises a receiving unit 14 which receives speech data and uses that data to output speech 15. The characteristics of the speech are altered by processing unit 10 based upon the listener's current background noise before the speech is output to enhance its intelligibility to a listener. An analysis unit 12 determines the type and level of the background noise by a microphone 13 and decision unit 11 determines whether the speech currently received would be intelligible to an average listener in the current background noise. If unit 11 determines that the speech would be unintelligible, then processing unit 10 alters the speech before passing it to the output to make the speech more intelligible. Preferably the speech characteristics are altered by altering line spectral pair data representing the speech.

Noise suppression

A network noise suppressor includes means (113) for partially decoding a CELP coded bit-stream. Means (116) determine a noise suppressing filter H(z) from the decoded parameters. Means (118, 120) use this filter to determine modified LP and gain parameters. Means (122) overwrite corresponding parameters in the coded bit-stream with the modified parameters.

A Speech Processing System and Method

Apparatus and method for privacy enhancement

SYSTEM AND PROCEDURE FOR SIGNAL PROCESSING

IMPROVEMENT OF THE SPRACHVERSTÄNDLICHKEIT IN A MOBILE COMMUNICATION DEVICE BY TAXES OF THE FUNCTION OF A VIBRATOR AS A FUNCTION OF THE BACKGROUND NOISE

PROCEDURE AND DEVICE FOR THE SQUELCH

LANGUAGE TRANSFORMATION EQUIPMENT AND PROCEDURE

IMPROVEMENT OF THE SPRACHVERSTÄNDLICHKEIT WITH A PSYCHOAKUSTI MODEL AND A OVER-SCANNED FILTER BANK

PROCEDURE, DEVICE AND PROGRAM CODE FOR THE TRANSFORMATION OF VOICES

REWORK FOR THE REDUCTION OF THE QUANTIFICATION NOISE OF A CODER DURING THE DECODING

DEVICE AND PROCEDURE FOR THE DISTRIBUTED GAIN CONTROL FOR THE SPECTRAL IMPROVEMENT

METHODE ZUR TRENNUNG VON SIGNALPFADEN UND ANWENDUNG AUF DIE VERBESSERUNG VON SPRACHE MIT ELEKTRO-LARYNX

In order to improve the speech quality of an electric larynx (EL) speaker, the speech signal of which is digitized by suitable means, the following steps are carried out: a) dividing a single-channel speech signal into a series of frequency channels by transferring it from a time domain into a discrete frequency domain; b) filtering out the modulation frequency of the EL by way of a high-pass or notch filter, in each frequency channel; and c) back-transforming the filtered speech signal from the frequency domain into the time domain and combining it into a single-channel output signal.

METHODE ZUR TRENNUNG VON SIGNALPFADEN UND ANWENDUNG AUF DIE VERBESSERUNG VON SPRACHE MIT ELEKTRO-LARYNX

In order to improve the speech quality of an electric larynx (EL) speaker, the speech signal of which is digitized by suitable means, the following steps are carried out: a) dividing a single-channel speech signal into a series of frequency channels by transferring it from a time domain into a discrete frequency domain; b) filtering out the modulation frequency of the EL by way of a high-pass or notch filter, in each frequency channel; and c) back-transforming the filtered speech signal from the frequency domain into the time domain and combining it into a single-channel output signal.

DEVICE FOR THE EXTENSION OF THE RANGE OF AN AUDIO SIGNAL

CODE BOOK STRUCTURE AND SEARCH METHOD FOR THE LANGUAGE CODING

CLAY/TONE PROCESSING PROCEDURE AND DEVICE FOR THE ADJUSTMENT OF A HEARING AID FOR HEAR-OBSTRUCTED

System and method for adaptive audio signal generation, coding and rendering

Embodiments are described for an adaptive audio system that processes audio data comprising a number of independent monophonic audio streams. One or more of the streams has associated with it metadata that specifies whether the stream is a channel-based or object 5 based stream. Channel-based streams have rendering information encoded by means of channel name; and the object-based streams have location information encoded through location expressions encoded in the associated metadata. A codec packages the independent audio streams into a single serial bitstream that contains all of the audio data. This configuration allows for the sound to be rendered according to an allocentric frame of 10 reference, in which the rendering location of a sound is based on the characteristics of the playback environment (e.g., room size, shape, etc.) to correspond to the mixer's intent. The object position metadata contains the appropriate allocentric frame of reference information required to play the ...

Digital playback device and method and apparatus for spectrally modifying a digital audio signal

Sound processing with frequency transposition

Codebook structure and search for speech coding

Injection high frequency noise into pulse excitation for low bit rate celp

Method and apparatus for speech enhancement in a speech communication system

Method and device for enhancing the recognition of speech among speech-impaired individuals

An arrangement for demodulating speech signals discontinuously transmitted from a mobile unit

SPEECH SYNTHESIZING ARRANGEMENT HAVING AT LEAST TWO DISTORTION CIRCUITS

DETERMINING AND REMEDYING AUDIO QUALITY ISSUES IN A VOICE COMMUNICATION

A method (400) and apparatus for determining and remedying audio quality issues in a voice communication. One example electronic computing device (110) includes an electronic processor configured to receive, via a communication interface, a voice communication including a request from a communication device (105). The electronic processor is also configured to perform an analysis of the voice communication. The analysis includes disambiguating the voice communication. The electronic processor is also configured to store a profile of the voice communication associated with a state of the communication device (105) in a history of profiles (325), when disambiguating the voice communication is successful. When disambiguating the voice communication fails, the electronic processor determines whether the voice communication is associated with a profile in the history of profiles (325). When the voice communication is not associated with a profile, a command is transmitted to the communication ...

AUDIO SIGNAL

A computer device (100) for processing audio signals is described. The computer device (100) includes at least a processor and a memory. The computer device (100) is configured to receive a bitstream comprising a combined audio signal, the combined audio signal comprising a first audio signal including speech and a second audio signal. The computer device (100) is configured to compress the combined audio signal to provide a compressed audio signal. The computer device (100) is configured to control a dynamic range of the compressed audio signal to provide an output audio signal. In this way, a quality of the speech included in the output audio signal is improved.

ENCODER AND METHOD FOR ENCODING AN AUDIO SIGNAL WITH REDUCED BACKGROUND NOISE USING LINEAR PREDICTIVE CODING

It is shown an encoder for encoding an audio signal with reduced background noise using linear predictive coding. The encoder comprises a background noise estimator configured to estimate background noise of the audio signal, a background noise reducer configured to generate background noise reduced audio signal by subtracting the estimated background noise of the audio signal from the audio signal, and a predictor configured to subject the audio signal to linear prediction analysis to obtain a first set of linear prediction filter (LPC) coefficients and to subject the background noise reduced audio signal to linear prediction analysis to obtain a second set of linear prediction filter (LPC) coefficients. Furthermore, the encoder comprises an analysis filter composed of a cascade of time-domain filters controlled by the obtained first set of LPC coefficients and the obtained second set of LPC coefficients.

SYSTEM FOR ADAPTIVELY REDUCING NOISE IN SPEECH SIGNALS

A method and system are provided for adaptively reducing noise in frames of digitized audio signals that may include both speech and backgroun d noise. Frames of digitized audio signals are processed to determine what attenuation (if any) should be applied to the current frame of digitized aud io signals. Initially it is determined whether the current frame of digitized audio signals includes speech information, this determination being based upon an estimate of noise and on a speech threshold value. An attenuation value determined for the previous audio frame is modified based on this determination and applied to the current frame in order to minimize the background noise which thereby improves the quality of received speech. The attenuation applied to the audio frames is modified gradually on a frame-by-frame basis, each sample in a specific frame is attenuated using th e value calculated for that frame. The adaptive noise reduction system may be advantageously applied to telecommunication ...

METHOD FOR CONDITIONING A DIGITAL SPEECH SIGNAL

Pour conditionner un signal numérique de parole(s) traité par trames successives, on en effectue une analyse harmonique pour estimer une fréquence tonale sur chaque trame où il présente une activité vocale, et on le suréchantillonne à une fréquence de suréchantillonnage (fe) multiple de la fréquence tonale estimée.

Speech enhancement system for hearing aid - uses filters for adjusting speech signal spectral envelope by amplifying signal peaks

The speech enhancement system improves the comprehension of speech signals, by altering their spectral envelope, so that the amplitudes of the speech wave peaks are amplified and the depths of the troughs between these peaks are increased. The formation and alteration of the speech signal spectral envelope is effected with a min. delay, pref. using adaptive grid filters (9,10,11). The first of these filters (9) is supplied with a set of filter coefficients via an iterative process, with adaptive correction w.r.t. the variation in the speech signals. The remaining filters (10,11) are supplied with filter coefficients which are adjusted in accordance with the first filter. ADVANTAGE - Highly miniaturised, low current consumption and no discernible time delay during envelope adjustments.

DECODING METHOD AND DECODER FOR DIALOG ENHANCEMENT

宽带语音编解码器中的高频增强层编码

... 用于编码和解码输入信号(100)和提供合成的语音(110)的语音编码方法和设备，其中通过对仿真信号(150)高通滤波和着色获得合成语音(110)的高频部分(160)来提供处理过的仿真信号(154)。处理过的仿真信号(154)在输入信号(100)的激活语音周期通过第一缩放因子(114，144)进行缩放(530，540)，在非激活语音周期通过第二缩放因子(114和115，144和145)进行缩放，其中第一缩放因子(114，144)具有输入信号(100)的高频带特性，并且第二缩放因子(114和115，144和145)具有输入信号(100)的低频带特性。特别地，第二缩放因子(114和115，144和145)基于合成语音(110)的低频部分进行估算，并且仿真信号(150)的着色是基于具有输入信号(100)低频特性的线性预测编码系数(104)的。 ...

METHOD OF SENDING AND SOUND REPRODUCTION OF AUDIO INFORMATION

METHOD AND SYSTEM FOR LIMITING SOUND VOLUME CONTAINING CEMENT

L'invention concerne un téléphone de voiture (20) avec un système de limitation de volume sonore (25) comportant un récepteur d'entrée (21) et un émetteur de sortie (22) de téléphonie mobile aptes à communiquer par un réseau hertzien (RH) avec un poste distant (40), ainsi qu'un haut-parleur d'émission sonore (23) et un microphone de capture sonore (24) reliés respectivement au récepteur d'entrée (21) et à l'émetteur de sortie (22) via le système de limitation (25). Le système de limitation (25) comporte en liaison un module de détection d'empreinte de voix (27), un variateur de volume (30) et un équipement anti-écho (26). De plus, le module de détection (27) est agencé entre le récepteur d'entrée (21), et le variateur de volume (30), ce dernier étant relié au haut-parleur (23), et l'équipement anti-écho (25) est monté entre le microphone (24) et l'émetteur de sortie (22).

SYSTEM FOR TRANSFERRING WIDE-BAND SOUND SIGNALS

METHOD AND A SYSTEM FOR ENHANCING AN AUDIO SIGNAL

Procédé de rehaussement d'un signal audio destiné à être diffusé à au moins un auditeur cible, ledit procédé comprenant les étapes suivantes : - Recevoir un signal audio s(t), - Filtrer (201) le signal audio s(t) par un filtre de rehaussement fréquentiel dont le gabarit fréquentiel est déterminé à partir de valeurs statistiques d'écart de seuil d'audition, fonctions de la fréquence, caractéristiques dudit au moins un auditeur cible.

EFFICIENT PRE-ECHO ATTENUATION IN A DIGITAL AUDIO SIGNAL

L'invention se rapporte à un procédé de traitement d'atténuation de pré-écho dans un signal audionumérique décodé selon un décodage par transformée. Ce procédé comporte les étapes suivantes: - décomposition (E603) du signal décodé en au moins deux sous-signaux selon un critère de décomposition prédéterminé; - calcul (E604) de facteurs d'atténuation par sous-signal et par échantillon d'une zone de pré-écho préalablement déterminée; - atténuation (E605) de pré-écho dans la zone de pré-écho de chacun des sous-signaux par application des facteurs d'atténuation aux sous-signaux; et -obtention (E606) du signal atténué par addition des sous-signaux atténués. L'invention se rapporte aussi à un dispositif de traitement mettant en œuvre les étapes du procédé décrit, à un décodeur comportant un tel dispositif.

PERIODIC SIGNAL ENHANCEMENT SYSTEM

Method and system of environment-sensitive automatic speech recognition

Method and apparatus for audio intelligibility enhancement and computing apparatus

Method and apparatus for audio intelligibility enhancement and computing apparatus are provided. The method includes the following steps. Environment noise is detected by performing voice activity detection according to a detected audio signal from at least a microphone of a computing device. Noise information is obtained according to the detected environment noise and a first audio signal. A second audio signal is outputted by boosting the first audio signal under an adjustable headroom by the computing device according to the noise information and the first audio signal.

System and method for adaptive audio signal generation, coding and rendering

Embodiments are described for an adaptive audio system that processes audio data comprising a number of independent monophonic audio streams. One or more of the streams has associated with it metadata that specifies whether the stream is a channel-based or object-based stream. Channel-based streams have rendering information encoded by means of channel name; and the object-based streams have location information encoded through location expressions encoded in the associated metadata. A codec packages the independent audio streams into a single serial bitstream that contains all of the audio data. This configuration allows for the sound to be rendered according to an allocentric frame of reference, in which the rendering location of a sound is based on the characteristics of the playback environment (e.g., room size, shape, etc.) to correspond to the mixer's intent. The object position metadata contains the appropriate allocentric frame of reference information required to play the sound ...

Pick-up method and system based on microphone array

The invention relates to a pick-up method and system based on a microphone array; the method comprises the steps of 1, using the microphone array to pick up and output one of multiple speech signals for speech activation detection, and judging whether a speech activation signal occurs or not; if yes, executing step 2; if not, repeating the step 1; 2, performing sound source positioning on the multiple speech signals to obtain a sound source positioning direction; 3, subjecting the speech signal of the sound source positioning direction to speech augmentation to obtain an augmented speech signal; 4, subjecting the augmented speech signal to speech wakeup detection, and judging whether speech wakeup is detected or not; if yes, executing step 5; if not, repeating the step 1; 5, allowing the microphone array to pick up and output the multiple speech signals; 6, processing the multiple speech signals as one signal that is output finally as picked speech. Speech signals can be better picked up ...

Voice activity detector (VAD)based multiple-microphone acoustic noise suppression

Acoustic noise suppression is provided in multiple-microphone systems using Voice Activity Detectors (VAD). A host system receives acoustic signals via multiple microphones. The system also receives information on the vibration of human tissue associated with human voicing activity via the VAD. In response, the system generates a transfer function representative of the received acoustic signals upon determining that voicing information is absent from the received acoustic signals during at least one specified period of time. The system removes noise from the received acoustic signals using the transfer function, thereby producing a denoised acoustic data stream.

Mixing apparatus, mixing method, and non-transitory computer-readable recording medium

A mixing apparatus having a stereo output includes: a first signal processor that mixes a first signal and a second signal in a first channel; a second signal processor that mixes a third signal and a fourth signal in a second channel; a third channel that processes a weighted sum of a signal of the first channel and a signal of the second channel; and a gain deriving part that generates a gain mask commonly used in the first channel and the second channel, wherein the gain deriving part determines a first gain commonly applied to the first signal and the third signal, and a second gain commonly applied to the second signal and the fourth signal, so that predetermined conditions for simultaneous gain generation are satisfied at least at the first channel and the second channel among the first channel, the second channel, and the third channel.

Call Method of Terminal and Terminal Using Call Method

A call method of a terminal and a terminal using the call method, are provided to adjust voice quality of a call in real time. The method includes analyzing a spectral component of a voice signal during a call and selecting a corresponding frequency response channel according to an analysis result of the spectral component of the voice signal.

Digital signal processing apparatus and digital signal processing method

A digital signal of which input data has been segmented as block each having a predetermined data amount and highly efficiently encoded along with an adjacent block is decoded, edited, and then highly efficiently encoded. A delay that takes place in such signal processes is compensated. Thus, part of a digital signal that has been highly efficiently encoded digital signal can be edited.

ELECTRONIC APPARATUS AND CONTROLLING METHOD THEREOF

Provided are an electronic apparatus and a controlling method thereof. The electronic apparatus includes an inputter and a processor configured to, based on receiving an audio signal through the inputter, obtain a speech intelligibility for the audio signal, and modify the audio signal so that the speech intelligibility becomes a target intelligibility that is set based on scene information regarding a type of audio included in the audio signal, and the type of audio includes at least one of a sound effect, shouting, music, or a speech.

Detecting and reducing feedback

A computer-implemented method to detect and reduce feedback in an audio signal is disclosed. The method may include obtaining an audio signal. The method may further include separating the audio signal into a plurality of frequency bands. The method may also include, for each frequency band of the plurality of frequency bands, determining whether the frequency band includes feedback. The method may further include, for each frequency band determined to include feedback, attenuating the frequency band. The method may also include combining each frequency band of the plurality of frequency bands to produce an output audio signal.

Method and system for estimating artificial high band signal in speech codec using voice activity information

A method and system for encoding and decoding an input signal, wherein the input signal is divided into a higher frequency band and a lower frequency band in the encoding and decoding processes, and wherein the decoding of the higher frequency band is carried out by using an artificial signal along with speech related parameters obtained from the lower frequency band. In particular, the artificial signal is scaled before it is transformed into an artificial wideband signal containing colored noise in both the lower and the higher frequency band. Additionally, voice activity information is used to define speech periods and non-speech periods of the input signal. Based on the voice activity information, different weighting factors are used to scale the artificial signal in speech periods and non-speech periods.

SEPARATING DESIRED AUDIO CONTENT FROM UNDESIRED CONTENT

The present disclosure provides new variants of non-negative matrix factorization suitable for separating desired audio content from undesired audio content. In certain embodiments, a multi-dimensional non-negative representation of an audio signal is decomposed into desired content and undesired content by performing convolutional non-negative matrix factorization (CNMF) on multiple layers, each layer having a respective non-negative matrix representation. In certain embodiments, the desired content is represented by a first dictionary and the undesired content is represented by a second dictionary, and sparsity is imposed on activations of basic elements of the first or the second dictionary, wherein a degree of sparsity is controlled by setting a minimum number of components with significant activations of the first or second dictionary, respectively.

RESPIRATOR MASK SPEECH ENHANCEMENT APPARATUS AND METHOD

Speech enhancement apparatus and respirator masks including speech enhancement apparatus, as well as methods of enhancing speech transmission for the wearer of a respirator mask are described herein. In one or more embodiments, the speech enhancement apparatus and methods described herein detect acoustic energy within a first frequency range in the clean air envelope of a respirator mask and deliver compensating acoustic energy outside of the clean air envelope using a speaker. The compensating acoustic energy, in one or more embodiments, exhibits a predetermined attenuated amplitude profile such that the compensating acoustic energy has an amplitude less than 6 dB greater than the acoustic attenuation profile of the mask body over at least 90% of a predetermined attenuated frequency range.

POST-PROCESSING GAINS FOR SIGNAL ENHANCEMENT

A method, an apparatus, and logic to post-process raw gains determined by input processing to generate post-processed gains, comprising using one or both of delta gain smoothing and decision-directed gain smoothing. The delta gain smoothing comprises applying a smoothing filter to the raw gain with a smoothing factor that depends on the gain delta: the absolute value of the difference between the raw gain for the current frame and the post-processed gain for a previous frame. The decision-directed gain smoothing comprises converting the raw gain to a signal-to-noise ratio, applying a smoothing filter with a smoothing factor to the signal-to-noise ratio to calculate a smoothed signal-to-noise ratio, and converting the smoothed signal-to-noise ratio to determine the second smoothed gain, with smoothing factor possibly dependent on the gain delta.

Digital signal processing techniques for improving audio clarity and intelligibility

Methods and apparatus are described for effecting multi-band processing and automatic gain control of an original sampled signal. According to various implementations, attack and release multipliers are applied to signal samples in a variety of ways to achieve a variety of effects.

AUTOMATIC GAIN CONTROL BASED ON MACHINE LEARNING LEVEL ESTIMATION OF THE DESIRED SIGNAL

Method includes receiving, through a plurality of channels, audio data corresponding to a plurality of frequency ranges; determining, for each channel's frequency ranges, speech audio and/or noise energy level using a model trained by machine learning; determining a speech signal with removed noise for each channel; determining one or more statistical values associated with an energy level of a channel's speech signal with the removed noise; determining a strongest channel that has highest statistical values associated with an energy level of a speech signal; determining that the one or more statistical values associated with the energy level of the strongest channel's speech signal satisfy a threshold condition; comparing statistical values associated with an energy level of a speech signal of each channel with those of the strongest channel; and determining whether to update a gain value for a channel based on the channel's statistical values associated with the energy level.

ENHANCEMENT OF INTELLIGIBILITY IN NOISY ENVIRONMENT

Provided are methods and systems for enhancing the intelligibility of an audio (e.g., speech) signal rendered in a noisy environment, subject to a constraint on the power of the rendered signal. A quantitative measure of intelligibility is the mean probability of decoding of the message correctly. The methods and systems simplify the procedure by approximating the maximization of the decoding probability with the maximization of the similarity of the spectral dynamics of the noisy speech to the spectral dynamics of the corresponding noise-free speech. The intelligibility enhancement procedures provided are based on this principle, and all have low computational cost and require little delay, thus facilitating real-time implementation.

METHOD AND APPARATUS FOR PROCESSING AN AUDIO SIGNAL, AUDIO DECODER, AND AUDIO ENCODER

A method is described that processes an audio signal. A discontinuity between a filtered past frame and a filtered current frame of the audio signal is removed using linear predictive filtering.

METHOD AND APPARATUS FOR DETERMINING A MEASURE OF SPEECH INTELLIGIBILITY

A method of estimating speech intelligibility is disclosed. The method comprises the steps of providing at least a first time-dependent signal derived from a first auditory stimulus and a corresponding first measured EEG response; comparing at least part of the first signal with at least part of the first measured EEG response in order to determine a signal-response latency difference; comparing the signal-response latency difference to a reference value; and deriving a measure of speech intelligibility based on the comparison of the signal-response latency difference and the reference value.

METHOD OF COMPENSATING A PROCESSED AUDIO SIGNAL

ПОВЫШЕНИЕ РАЗБОРЧИВОСТИ РЕЧИ С ПОМОЩЬЮ ЧЕТКОСТИ ГОЛОСА

Изобретение относится к обработке аудиосигнала, в частности к процессору или способу обработки для повышения разборчивости речи и очистки зашумленного речевого аудиосигнала. Техническим результатом является повышение разборчивости речи и четкости голоса. Указанный результат достигается тем, что в способе улучшения речевых компонентов аудиосигнала, состоящего из речевых и шумовых компонентов, изменяют аудиосигнал из временной области во множество поддиапазонов в частотной области, с созданием множественных сигналов поддиапазона, обрабатывают поддиапазоны аудиосигнала, причем упомянутая обработка включает в себя управление усилением аудиосигнала в некоторых из упомянутых поддиапазонов, при этом усилением в поддиапазоне управляют путем аддитивной/субстрактивной или мультипликативной комбинации а) снижения усиления в поддиапазоне при увеличении оценки уровня шумовых компонентов в поддиапазоне, при этом оценку уровня шумовых компонентов в поддиапазоне определяют при отсутствии речи, и b) увеличения ...

СПОСОБ И УСТРОЙСТВО ДЛЯ ЧАСТОТНО-ИЗБИРАТЕЛЬНОГО ВЫДЕЛЕНИЯ ОСНОВНОГО ТОНА СИНТЕЗИРОВАННОЙ РЕЧИ

Изобретение относится к способу и устройству для последующей обработки декодированного звукового сигнала, причем декодированный звуковой сигнал делят на совокупность сигналов частотных поддиапазонов и последующую обработку применяют к, по меньшей мере, одному из совокупности сигналов частотных поддиапазонов. После последующей обработки этого, по меньшей мере, одного сигнала частотного поддиапазона, сигналы частотных поддиапазонов суммируют для создания выходного декодированного звукового сигнала, подвергнутого последующей обработке. Таким образом, последующую обработку локализуют в нужном(ых) поддиапазоне или поддиапазонах, оставляя другие поддиапазоны практически неизменными. Технический результат - повышение воспринимаемого качества декодированного звукового сигнала. 3 н. и 51 з.п ф-лы, 14 ил.

РАСЧЕТ И РЕГУЛИРОВКА ВОСПРИНИМАЕМОЙ ГРОМКОСТИ И/ИЛИ ВОСПРИНИМАЕМОГО СПЕКТРАЛЬНОГО БАЛАНСА ЗВУКОВОГО СИГНАЛА

Изобретение относится к обработке звуковых сигналов, относящейся к измерению и регулированию воспринимаемой громкости звука и/или воспринимаемого спектрального баланса звукового сигнала. Обработка звуковых сигналов полезна, например, в одном или более из: регулировки уровня громкости с компенсацией громкости, автоматической регулировки усиления, регулировки динамического диапазона (в том числе, например, ограничителях, компрессорах, расширителях динамического диапазона и т.п.), динамической коррекции и компенсации шумовых фоновых помех в средах воспроизведения аудио. В различных вариантах осуществления параметры модификации получаются для модифицирования звукового сигнала, для того чтобы уменьшать разность между его удельной громкостью и целевой удельной громкостью. Технический результат - повышение разборчивости звукового сигнала. 4 н. и 22 з.п. ф-лы, 19 ил.

РАСШИРЕНИЕ ПОЛОСЫ ЧАСТОТ ГАРМОНИЧЕСКОГО АУДИОСИГНАЛА

Изобретение относится к средствам для управления усилениями в полосах в расширенной области полосы частот на основе информации о положениях пиков. Технический результат заключается в повышении качества расширения полосы частот гармонических аудиосигналов. Принимают множество значений усиления, ассоциированных с полосой b частот, и множество соседних полос частот для полосы b. Определяют, содержит ли реконструированная соответствующая полоса b’ частот спектральный пик. Когда полоса b’ содержит спектральный пик, значение усиления, ассоциированное с полосой b’, устанавливают как первое значение на основе принятого множества значений усиления; и в противном случае, значение усиления устанавливают как второе значение на основе принятого множества значений усиления. 4 н. и 8 з.п. ф-лы, 10 ил.

ГИБРИДНОЕ УСИЛЕНИЕ РЕЧИ С КОДИРОВАНИЕМ ФОРМЫ СИГНАЛА И ПАРАМЕТРИЧЕСКИМ КОДИРОВАНИЕМ

Изобретение относится к средствам для гибридного усиления речи. Технический результат заключается в повышении слышимости речевого содержимого звукового сигнала относительно неречевого звукового содержимого. Предлагаемый способ гибридного усиления речи использует усиление с параметрическим кодированием при некоторых состояниях сигнала и усиление с кодированием формы сигнала при остальных состояниях сигнала. Другими аспектами являются способы генерирования битового потока, указывающего на звуковую программу, включающую речевое и другое содержимое, так что гибридное усиление речи может быть выполнено в отношении программы, декодер, включающий буфер, который хранит по меньшей мере один сегмент кодированного битового аудиопотока, сгенерированного любым вариантом осуществления способа изобретения, и система или устройство, выполненное с возможностью выполнения любого варианта осуществления способа изобретения. По меньшей мере некоторые из операций усиления речи выполнены принимающим аудиодекодером ...

ОПТИМИЗАЦИЯ ГРОМКОСТИ И ДИНАМИЧЕСКОГО ДИАПАЗОНА ЧЕРЕЗ РАЗЛИЧНЫЕ УСТРОЙСТВА ВОСПРОИЗВЕДЕНИЯ

Изобретение относится к области обработки аудиосигналов. Технический результат заключается в повышении эффективности обработки аудиосигналов. Технический результат достигается за счет того, что контейнер метаданных начинается с синхрослова, идентифицирующего начало контейнера метаданных, одни или более рабочие данные метаданных включают в себя параметр, указывающий профиль сжатия динамического диапазона (DRC), выбранный из множества профилей DRC, при этом каждый из множества профилей DRC соответствует уникальной кривой сжатия с ассоциированными постоянными времени, и упомянутые одни или более рабочие данные метаданных следуют за защитными данными, которые могут быть использованы для дешифрования, аутентификации или проверки допустимости упомянутых одних или более рабочих данных метаданных. 10 з.п. ф-лы, 16 ил.

СИСТЕМА, СПОСОБ И ПОСТОЯННЫЙ МАШИНОЧИТАЕМЫЙ НОСИТЕЛЬ ДАННЫХ ДЛЯ ГЕНЕРИРОВАНИЯ, КОДИРОВАНИЯ И ПРЕДСТАВЛЕНИЯ ДАННЫХ АДАПТИВНОГО ЗВУКОВОГО СИГНАЛА

Изобретение относится к области обработки аудиоданных. Технический результат заключается в повышении качества обработки звуковых сигналов, подаваемых на громкоговорители. Технический результат достигается за счет заключения ряда монофонических аудиопотоков и метаданных в битовом потоке для передачи в систему представления, выполненную с возможностью представления ряда монофонических аудиопотоков в ряд сигналов, подаваемых на громкоговорители, соответствующих громкоговорителям в среде проигрывания, при этом громкоговорители массива громкоговорителей размещают в определенных положениях в пределах среды проигрывания, и при этом элементы метаданных, связанные с каждым соответствующим монофоническим аудиопотоком на основе объектов, указывают, запрещено ли представление соответствующего монофонического аудиопотока в один или более определенных сигналов, подаваемых на громкоговорители, ряда сигналов, подаваемых на громкоговорители, так что соответствующий монофонический аудиопоток на основе объектов ...

КОНТРОЛЛЕР ВЫРАВНИВАТЕЛЯ ГРОМКОСТИ И СПОСОБ УПРАВЛЕНИЯ

СПОСОБ ОСУЩЕСТВЛЕНИЯ ЭКВАЛАЙЗЕРА В ДЕКОДЕРЕ АУДИОСИГНАЛА И УСТРОЙСТВО ДЛЯ ЕГО ОСУЩЕСТВЛЕНИЯ

... 1. Способ декодирования аудиосигнала, причем способ содержит этапы, на которых: ! преобразуют данные выборки поддиапазона аудиосигнала в элементы информации диапазона частот; ! регулируют элементы информации диапазона частот в соответствии с вводом; и ! преобразуют отрегулированные элементы информации диапазона частот в данные выборки поддиапазона. ! 2. Способ по п.1, дополнительно содержащий этап, на котором отображают отрегулированные элементы информации диапазона частот. ! 3. Способ по п.1, в котором этап, на котором преобразуют данные выборки поддиапазона в элементы информации диапазона частот, содержит этапы, на которых: ! детектируют частотные составляющие из данных выборки поддиапазона; и ! группируют детектированные частотные составляющие в диапазоны частот, и отображают каждую группу на один из множества элементов информации диапазона частот. ! 4. Способ по п.3, в котором этап, на котором регулируют элементы информации диапазона частот, содержит этапы, на которых: ! принимают входную ...

КОНТРОЛЛЕР ВЫРАВНИВАТЕЛЯ ГРОМКОСТИ И СПОСОБ УПРАВЛЕНИЯ

СИСТЕМА И СПОСОБ ДЛЯ ГЕНЕРИРОВАНИЯ, КОДИРОВАНИЯ И ПРЕДСТАВЛЕНИЯ ДАННЫХ АДАПТИВНОГО ЗВУКОВОГО СИГНАЛА

Sprachsignalinterpolationseinrichtung

Sprachsignalinterpolationsvorrichtung, umfassend: ein Tonhöhenwellenformsignalerzeugungsmittel zum Erfassen eines Spracheingabesignals, das für eine Sprach-Wellenform repräsentativ ist, und im Wesentlichen Angleichen einer Zeitdauer eines Abschnitts, der einer Tonhöheneinheit des Spracheingabesignals entspricht, um das Spracheingabesignal in ein Tonhöhenwellenformsignal umzuwandeln; ein Spektrumableitungsmittel zum Erzeugen von Daten, die für ein Spektrum des Spracheingabesignals repräsentativ sind, gemäß dem Tonhöhenwellenformsignal; ein Mittelwertbildungsmittel zum Erzeugen von Bemittelten Daten, die für ein Spektrum einer Verteilung von Durchschnittswerten jeweiliger Spektrumkomponenten des Spracheingabesignals repräsentativ sind, gemäß mehreren Datenteilstücken, die von dem Spektrumableitungsmittel erzeugt wurden; und ein Sprachsignalwiederherstellungsmittel zum Erzeugen eines Sprachausgabesignals, das für Sprache repräsentativ ist, die ein Spektrum aufweist, das durch die gemittelten ...

Audio human verification

A system generates an audio challenge that includes a first voice and one or more second voices, the first voice being audibly distinguishable, by a human, from the one or more second voices. The first voice conveys first information and the second voice conveys second information. The system provides the audio challenge to a user and verifies that the user is human based on whether the user can identify the first information in the audio challenge.

Post-noise suppression processing to improve voice quality

Provided are methods and systems for improving quality of speech communications. The method may be for improving quality of speech communications in a system having a speech encoder configured to encode a first audio signal using a first set of encoding parameters associated with a first noise suppressor. A method may involve receiving a second audio signal at a second noise suppressor which provides much higher quality noise suppression than the first noise suppressor. The second audio signal may be generated by a single microphone or a combination of multiple microphones. The second noise suppressor may suppress the noise in the second audio signal to generate a processed signal which may be sent to a speech encoder. A second set of encoding parameters may be provided by the second noise suppressor for use by the speech encoder when encoding the processed signal into corresponding data.

Method and system for reconstructing speech from an input signal comprising whispers

A system for reconstructing speech from an input signal comprising whispers is disclosed. The system comprises an analysis unit configured to analyse the input signal to form a representation of the input signal; an enhancement unit configured to modify the representation of the input signal to adjust a spectrum of the input signal, wherein the adjusting of the spectrum of the input signal comprises modifying a bandwidth of at least one formant in the spectrum to achieve a predetermined spectral energy distribution and amplitude for the at least one formant; and a synthesis unit configured to reconstruct speech from the modified representation of the input signal.

Voice correction device, voice correction method, and recording medium storing voice correction program

A voice correction device includes a detector that detects a response from a user, a calculator that calculates an acoustic characteristic amount of an input voice signal, an analyzer that outputs an acoustic characteristic amount of a predetermined amount when having acquired a response signal due to the response from the detector, a storage unit that stores the acoustic characteristic amount output by the analyzer, a controller that calculates an correction amount of the voice signal on the basis of a result of a comparison between the acoustic characteristic amount calculated by the calculator and the acoustic characteristic amount stored in the storage unit, and a correction unit that corrects the voice signal on the basis of the correction amount calculated by the controller.

VOICE CLARIFICATION APPARATUS

The voice clarification apparatus includes a plurality of band-pass filters that respectively extract a plurality of band components, which are included in a voice band, from an input audio signal; a gain determination unit that determines a gain according to the level of a signal of a band component which is extracted by at least one band-pass filter of the plurality of band-pass filters; a level adjustment unit that adjusts the levels of signals of the plurality of band components which are extracted by the plurality of band-pass filters using the gain; and a first addition unit that adds a signal which is based on the audio signal to a signal in which the gain is adjusted by the level adjustment unit, and outputs a signal obtained through the addition. 1. A voice clarification apparatus comprising:a plurality of band-pass filters that respectively extract a plurality of band components, which are included in a voice band, from an input audio signal;a gain determination unit that determines a gain according to a level of a signal of a band component which is extracted by at least one band-pass filter of the plurality of band-pass filters;a level adjustment unit that adjusts levels of signals of the plurality of band components which are extracted by the plurality of band-pass filters using the gain; anda first addition unit that adds a signal which is based on the audio signal to a signal in which the gain is adjusted by the level adjustment unit, and outputs a signal obtained through the addition.2. The voice clarification apparatus according to claim 1 ,wherein the gain determination unit includes a conversion unit which converts input levels based on a signal indicative of voice components into a gain which has predetermined input and output characteristics, andwherein the conversion unit outputs the gain which is greater than “1” when an absolute value of a level of the signal indicative of the voice components is equal to or less than a threshold, and outputs ...

Method of simultaneously transforming a plurality of voice signals input to a communications system

A method of simultaneously transforming at least two input voice signals x i of a communications system ( 30 ), each input voice signal x i being received at a specific reception frequency F i and corresponding to the voice of a remote party communicating with a user of the communications system ( 30 ). During an initialization stage, a transformation T i is allocated to at least one reception frequency F i of the input voice signals x i , and during a utilization stage, transformations T i are applied simultaneously to the input voice signals x i as a function of the reception frequencies F i , modifying at least one characteristic of each of the input voice signals x i . Thus, the voice of each remote party in communication with the user of the communications system ( 30 ) is modified artificially by a transformation T i , thereby making it easier for the user to perceive and discriminate between simultaneous voices from the remote parties.

Binaural enhancement of tone language for hearing assistance devices

Disclosed herein, among other things, are methods and apparatus for binaural enhancement of tone language for hearing assistance devices. One aspect of the present subject matter includes a method for enhancing pitch in a hearing assistance system having a first and second hearing assistance device. A signal is received using a microphone of the first hearing assistance device. Pitch detection is performed on the signal to obtain a pitch value. The pitch value is wirelessly transmitted from the first hearing assistance device to the second hearing assistance device. In various embodiments, the pitch value of the first hearing assistance device is combined with a pitch value of the second hearing assistance device. The gain is adjusted based on the combined pitch value, in various embodiments.

Adjustment apparatus and method

A disclosed adjustment apparatus includes: a calculation unit that calculates a ratio between a first frequency characteristic in a first frequency bandwidth of voice signals and a second frequency characteristic in a second frequency bandwidth of the voice signals, which is higher than the first frequency bandwidth, and calculates an adjustment amount for adjusting at least a portion of a frequency characteristic of the voice signals so that the calculated ratio approaches a predetermined reference, when the calculated ratio does not satisfy the predetermined reference; and a modification unit that modifies at least the portion of the frequency characteristic of the voice signals according to the adjustment amount.

Communication and speech enhancement system

A communication and speech enhancement system featuring a first transducer designed to be temporarily affixed to a human such as a hospital patient to convert the audible vibrations of human speech into an electrical signal. The transducer provides this electrical signal to one or more electronic modules which modify and enhance the signal. The enhanced signal may then be amplified and converted back into audible sound by means of a second transducer. A user of the system controls the electronic modules through a user interface. In an embodiment, one or both of the user interface and second transducer feature smooth surfaces amenable to cleaning and sterilizing with liquid agents.

Communication and speech enhancement system

A communication and speech enhancement system featuring a first transducer designed to be temporarily affixed to a human such as a hospital patient to convert the audible vibrations of human speech into an electrical signal. The transducer provides this electrical signal to one or more electronic modules which modify and enhance the signal. The enhanced signal may then be amplified and converted back into audible sound by means of a second transducer. A user of the system controls the electronic modules through a user interface. In an embodiment, one or both of the user interface and second transducer feature smooth surfaces amenable to cleaning sterilizing with liquid agents.

Signal processing device, sound-reproduction system, and sound reproduction method

A signal processing device includes: a processor; and a memory having instructions. The instructions, when executed by the processor, cause the signal processing device to perform operations. The operations include performing a modulation processing of modulating a sound signal by using a modulation parameter based on an interaural phase difference at a listening position of the sound signal.

ENHANCEMENT OF NOISY SPEECH BASED ON STATISTICAL SPEECH AND NOISE MODELS

A system for enhancement of noisy speech comprises an input unit is configured to subdivide the spectrum of the input signal into a plurality of frequency sub-bands and to provide time-frequency coefficients X(k,m) for a sequence [X(k, m′−D+1) . . . X(k,m′)] of observable noisy signal samples for each of said frequency sub-bands, where k and m are frequency and time indices, respectively, and D is larger than 1. The system further comprises enhancement processing unit configured to receive X(k,m) and to provide enhanced time-frequency coefficients Ŝ(k, m), a storage for statistical model(s) of speech and for statistical model(s) of noise, and an optimizing unit configured to provide said enhanced time-frequency coefficients Ŝ(k,m) using said statistical model of speech and said statistical model of noise, while considering said sequence [X(k, m′−D+1) . . . X(k, m′)] of observable noisy signal samples. Thereby the enhancement processing unit is able to determine the enhanced time-frequency coefficients based on the time-frequency coefficients for each of said frequency sub-bands. 1. A method for enhancement of speech in noise , the method comprising:providing a noisy input signal in a plurality of frequency sub-bands (k);for each of said frequency sub-bands providing time-frequency coefficients X(k,m) corresponding to a sequence [X(k,m′−D+1) . . . X(k,m′)] of observable noisy signal samples, where k and m are frequency and time indices, respectively, and D is larger than 1,enhancing said time-frequency coefficients X(k,m) thereby providing enhanced time-frequency coefficients Ŝ(k,m);providing a statistical model of speech;providing a statistical model of noise;providing said enhanced time-frequency coefficients Ŝ(k,m) using said statistical model of speech and said statistical model of noise, while considering said sequence [X(k, m′−D+1) . . . X(k,m′)] of observable noisy signal samples.2. The method according to wherein said statistical model of speech comprises a ...

VOICE EMPHASIS DEVICE

An input signal analyzer determines a boundary frequency within the limit of a range which does not exceed a first frequency from the mode of an input signal. A spectrum compressor compresses a power spectrum of frequencies in a band higher than the first frequency in a frequency direction. A gain corrector performs a gain correction on the compressed power spectrum. A spectrum synthesizer reflects the power spectrum outputted from the gain corrector in a band determined by both the first frequency and the boundary frequency. A frequency-to-time converter converts both a synthesized power spectrum provided by the spectrum synthesizer and a phase spectrum of the input signal into ones in the time domain, and outputs these spectra. 1. A voice emphasis device comprising:a time-to-frequency converter that converts an input signal in a time domain into a power spectrum which is a signal in a frequency domain;an input signal analyzer that analyzes a mode of said input signal from said power spectrum;a band determinator that determines a boundary frequency within a limit of a range which does not exceed a predetermined first frequency from the mode of said input signal;a spectrum compressor that compresses a power spectrum of frequencies in a band higher than said first frequency in a frequency direction;a spectrum synthesizer that reflects said compressed power spectrum in a band determined by both said first frequency and said boundary frequency; anda frequency-to-time converter that converts both a synthesized power spectrum outputted from said spectrum synthesizer and a phase spectrum of said input signal into ones in the time domain, to acquire an emphasized signal.2. The voice emphasis device according to claim 1 , wherein a gain corrector that claim 1 , by correcting the power spectrum compressed by said spectrum compressor in such a way that power of the power spectrum before the compression in a band on which said spectrum compressor performs the compression is ...

MULTI-STREAM TARGET-SPEECH DETECTION AND CHANNEL FUSION

Audio processing systems and methods include an audio sensor array configured to receive a multichannel audio input and generate a corresponding multichannel audio signal and target-speech detection logic and an automatic speech recognition engine or VoIP application. An audio processing device includes a target speech enhancement engine configured to analyze a multichannel audio input signal and generate a plurality of enhanced target streams, a multi-stream target-speech detection generator comprising a plurality of target-speech detector engines each configured to determine a probability of detecting a specific target-speech of interest in the stream, wherein the multi-stream target-speech detection generator is configured to determine a plurality of weights associated with the enhanced target streams, and a fusion subsystem configured to apply the plurality of weights to the enhanced target streams to generate an enhancement output signal. 1. A system comprising:a target-speech enhancement engine configured to receive a multichannel audio input signal and generate a plurality of enhanced target streams based on the received multichannel audio input signal, each of the plurality of enhanced target streams being generated according to different enhancement separation criteria; anda fusion subsystem configured to enhance a target audio signal associated with the multichannel audio input signal based at least in part on the plurality of enhanced target streams.2. The system of claim 1 , wherein the enhancement separation criteria include at least one of an adaptive spatial filtering algorithm claim 1 , a beamforming algorithm claim 1 , a blind source separation algorithm claim 1 , a single channel enhancement algorithm claim 1 , or a neural network.3. The system of claim 1 , further comprising:an audio sensor array configured to detect sound in an environment and generate the multichannel audio input signal based on the detected sound.4. The method of claim 3 , ...

Method for Processing an Acoustic Speech Input Signal and Audio Processing Device

The invention relates to a method for processing an acoustic input signal, preferably a speech signal, said method comprising the following steps: a) receiving a digital representation (S) of an acoustic input signal, b) calculating at least one statistical parameter (P) of the digital representation (S) of the acoustic input signal, c) calculating a compression ratio function (CR) based—on a prescribed constant compression ratio (CR), said prescribed constant compression ratio (CR) uniformly mapping acoustic input signals of a selected magnitude to acoustic output signals of a selected magnitude, and—on at least one statistical parameter (P) calculated in step b), and d) applying the non-uniform compression ratio function (CR) according to step c) on the digital representation (S) of the acoustic input signal delivering a digital representation (S) of an enhanced acoustic output signal. 1. A method for processing an acoustic input signal , the method comprising:a) receiving a digital representation of an acoustic input signal,b) calculating at least one statistical parameter of the digital representation of the acoustic input signal, on a prescribed constant compression ratio, where the prescribed constant compression ratio uniformly maps acoustic input signals of a selected magnitude to acoustic output signals of a selected magnitude, and', 'on at least one statistical parameter calculated in step b),, 'c) calculating a compression ratio function based'}wherein the compression ratio function deviates from the prescribed constant compression ratio by including a non-uniform mapping of acoustic input signals of a selected magnitude to acoustic output signals of a selected magnitude, wherein the non-uniformity of the mapping procedure is determined based on at least one statistical parameter calculated according to step b), andd) applying the non-uniform compression ratio function according to step c) on the digital representation of the acoustic input signal to ...

Speech intelligibility detection

Methods and systems are provided for enhancing speech intelligibility in electronic devices. During outputting of acoustic signal via an electronic device, measurement of forces applied by user of the electronic device against the device (or enclosure thereof) may be obtained. The force measurements may be used to assess and/or estimate the listening intelligibility experienced by the user. Further, the force measurements may be used to control or adjust a listening intelligibility stage applied during generation and/or processing of the acoustic signals that are outputted via the electronic device. In some instances, an audio input, corresponding to ambient noise affecting intelligibility, may be obtained, and may be used to control or assist in controlling the listening intelligibility stage.

Processing spoken commands to control distributed audio outputs

A system that is capable of controlling multiple entertainment systems and/or speakers using voice commands. The system receives voice commands and may determine audio sources and speakers indicated by the voice commands. The system may generate audio data from the audio sources and may send the audio data to the speakers using multiple interfaces. For example, the system may send the audio data directly to the speakers using a network address, may send the audio data to the speakers via a voice-enabled device or may send the audio data to the speakers via a speaker controller. The system may generate output zones including multiple speakers and may associate input devices with speakers within the output zones. For example, the system may receive a voice command from an input device in an output zone and may reduce output audio generated by speakers in the output zone.

NOISE ELIMINATION CIRCUIT

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 ...

Voice Activity Detector for Audio Signals

According to one aspect, a method for detecting voice activity is disclosed, the method including receiving a frame of an input audio signal, the input audio signal having an sample rate; dividing the frame into a plurality of subbands based on the sample rate, the plurality of subbands including at least a lowest subband and a highest subband; filtering the lowest subband with a moving average filter to reduce an energy of the lowest subband; estimating a noise level for each of the plurality of subbands; calculating a signal to noise ratio value for each of the plurality of subbands; and determining a speech activity level of the frame based on an average of the calculated signal to noise ratio values and a weighted average of an energy of each of the plurality of subbands. Other aspects include audio decoders that decode audio that was encoded using the methods described herein. 1. A method for determining voice activity in an audio signal , the method comprising: 'spitting the audio signal into a plurality of subbands by way of a sequence of filter banks, the plurality of subbands including at least a lowest subband and a highest subband;', 'receiving a frame of an input audio signal, the input audio signal having a sample rate;'} estimating a noise level for at least some of the plurality of subbands such that in each subband, a noise level estimator tracks the background noise level and a Signal-to-Noise Ratio (SNR) value', 'calculating a signal to noise ratio value for at least some of the plurality of subbands; and', 'determining a speech activity level based at least in part on an average of the calculated signal to noise ratio values and an average of an energy of at least some of the plurality of subbands,', 'wherein the method is performed with one or more computing devices., 'filtering the lowest subband with a linear filter to reduce an energy of the lowest subband;'}2. The method of further comprising smoothing the calculated signal to noise ratio ...

DEVICE AND METHOD FOR WIRELESSLY COMMUNICATING ON BASIS OF NEURAL NETWORK MODEL

Disclosed are a device and method for wirelessly communicating. The device according to one example embodiment of the present disclosure may comprise a transceiver and a controller connected to the transceiver, wherein the controller is configured to identify at least one additional sample on the basis of a digital signal by using a neural network model and upscale the digital signal by adding the at least one identified additional sample to a plurality of samples of the digital signal. 1. A device for wireless communication , the device comprising:a transceiver; and identify at least one additional sample by using a neural network model, based on a digital signal, and', 'upscale the digital signal by adding the identified at least one additional sample to a plurality of samples of the digital signal., 'a controller connected to the transceiver, wherein the controller is configured to2. The device of claim 1 , wherein to identify the at least one additional sample using the neural network model based on the digital signal claim 1 , the controller is further configured to:determine a weight in response to the digital signal; andidentify the at least one additional sample based on the digital signal and the weight.3. The device of claim 1 , wherein the controller is further configured to generate the neural network model by:obtaining a first output digital signal upscaled from a first input digital signal in response to the first input digital signal;obtaining a difference between the first output digital signal and one reference digital signal of a set of at least one reference digital signal; andobtaining a second output digital signal upscaled from a second input digital signal based on the difference and the second input digital signal.4. The device of claim 3 , wherein the difference is related to at least one sample not corresponding to a plurality of samples of the first output digital signal among a plurality of samples of the one reference digital signal.5. ...

SPEECH SIGNAL CASCADE PROCESSING METHOD, TERMINAL, AND COMPUTER-READABLE STORAGE MEDIUM

A method for improving speech signal intelligibility is performed at a device. A speech signal is obtained. A correspondence between the speech signal and a respective user group among different user groups having distinct voice characteristics is identified. Pre-encoding signal augmentation is performed on the speech signal with a respective pre-augmentation filtering coefficient that corresponds to the respective user group to obtain a group-specific pre-augmented speech signal. The device encodes the pre-augmented speech signal for subsequent transmission through the voice communication channel. An encoded version of the pre-augmented speech signal has reduced loss of signal quality as compared to an encoded version of the speech signal that is obtained without the pre-encoding signal augmentation. 1. A speech signal cascade processing method performed at a first terminal having one or more processors and memory storing a plurality of computer programs to be executed by the one or more processors , comprising:obtaining a speech signal from a second terminal via a voice communication channel, wherein the speech signal is processed with different audio codecs at the first terminal and the second terminal, respectively;performing feature recognition on the speech signal to determine a set of feature characteristics for the speech signal;when the set of feature characteristics matches a first set of predefined features, performing pre-augmented filtering on the speech signal by using a first set of pre-augmented filter coefficients, to obtain a pre-augmented speech signal;when the set of feature characteristics matches a second set of predefined features, performing pre-augmented filtering on the speech signal by using a second set of pre-augmented filter coefficients, to obtain the pre-augmented speech signal; andperforming cascade encoding/decoding to the pre-augmented speech signal to generate an augmented speech signal.2. The method according to claim 1 , wherein ...

Automatic Gain Adjustment for Improved Wake Word Recognition in Audio Systems

A mechanism is described for facilitating automatic gain adjustment in audio systems according to one embodiment. A method of embodiments, as described herein, includes determining status of one or more of gain settings, mute settings, and boost settings associated with one or more microphones based on a configuration of a computing device including a voice-enabled device. The method may further comprise recommending adjustment of microphone gain based on the configuration and the status of one or more of the gain, mute, and boost settings, and applying the recommended adjustment of the microphone gain. 1. An apparatus comprising:detection and observation logic to determine status of one or more of gain settings, mute settings, and boost settings associated with one or more microphones based on a configuration of the apparatus including a voice-enabled device;gain/boost adjustment and decision logic (“gain/boost logic”) to recommend adjustment of microphone gain based on the configuration and the status of one or more of the gain, mute, and boost settings; andgain/boost application logic (“application logic”) to apply the recommended adjustment of the microphone gain.2. The apparatus of claim 1 , further comprising mute enforcement logic to enforce muting of the one or more microphones based on the mute settings and according to a mute command3. The apparatus of claim 1 , wherein the recommended adjustment comprises a first gain compensation including muting one or more microphone signals before the one or more microphone signals enter a wake word recognizer (WWR) based on the configuration where the gain and boost settings do not modify signal reception capabilities of the WWR.4. The apparatus of claim 1 , wherein the recommended adjustment comprises a second gain compensation including compensating microphone boost and muting the one or more microphone signals before the one or more microphone signals enter the wake word recognizer (WWR) based on the configuration ...

SYSTEMS AND METHODS FOR SPEECH PROCESSING

Systems and methods described herein modify audio content on an electronic device. Embodiments can be configured to detect a mode of the electronic device to determine whether the device is in a telephone mode; receive a speech signal from a speech source while the device is in the telephone mode; and process the speech signal to improve the perceived quality of the speech at a recipient when the electronic device is in a telephone mode; wherein processing the speech signal to improve the perceived quality of the speech comprises, decreasing the signal level of audio content outside of a determined frequency band relative to the signal level of the audio content within the determined frequency band; and wherein the determined frequency band is a frequency band associated a vocal range of the anticipated speech content. 1. A method for modifying audio content on an electronic device , the method comprising:detecting an audio mode in which the electronic device is operating to determine a type of audio content processing to apply to audio content based on the detected audio mode, wherein the type of audio content processing comprises speech processing when the electronic device is detected to be in a speech-related audio mode, and music processing when the electronic device is detected to be in a playback audio mode;if the detected audio mode is a speech-related audio mode, receiving a speech signal from a speech source; andprocessing the speech signal to improve a perceived quality of the speech at a recipient; decreasing a signal level of audio content outside of a determined frequency band relative to a signal level of audio content within the determined frequency band; and', 'adjusting attack and release times of the speech signal based on sound events within the speech signal; and, 'wherein processing the speech signal to improve the perceived qualify of the speech compriseswherein the determined frequency band is a frequency band associated with a vocal range of ...

METHODS FOR HEARING-ASSIST SYSTEMS IN VARIOUS VENUES

A hearing-assist system for use in a venue in which the system includes circuitry inserted in a signal path between a program source feed of sound and hearing-assist units of users in that venue which improves the quality of sound heard by the users via the hearing-assist units. 1. A hearing-assist system for use in a venue intermediate a program source feed and hearing assist devices borne by patrons in the venue , the hearing-assist system adapted to modify the hearing quality of sound transmitted from the program source feed to the hearing assist devices , the hearing-assist system comprising:(a) processing circuitry configured to reduce selected high energy components of the so-transmitted sound;(a) processing circuitry configured to optimize selected components of the so-transmitted sound; and(c) processing circuitry configured to modify the dynamic range of the so-transmitted sound.2. The hearing-assist system defined in further including circuitry for introducing time delays to the signals corresponding to the sound received by the hearing assist devices.3. The hearing-assist system defined in in which the time delays are respectively different to correspond to different hearing needs.4. The hearing assist system defined in in which the time delays are respectively different to correspond to different locations of the hearing assist devices in the venue.5. A hearing-assist system for use in a venue intermediate a program source feed and hearing assist devices of patrons in the venue claim 3 , the hearing assist system adapted to improve the hearing quality of sound received by the hearing assist devices compared to the hearing quality of sound transmitted from the program source feed toward the hearing assist devices claim 3 , the hearing assist system comprising processing circuitry having at least one processing stage from a group consisting of a processing stage for modifying selected high energy components of the transmitted sound claim 3 , a processing ...

SYSTEM AND METHOD FOR PHONETIC HASHING AND NAMED ENTITY LINKING FROM OUTPUT OF SPEECH RECOGNITION

A system and method for named entity linking from the output of speech-to-text systems by using an approximate string matching that normalizes common sounds, removes ambiguities, removes silent consonants, and accounts for speech slurring for long names. Additionally, the system and method for named entity linking from the output of speech-to-text systems employs a hierarchical matching system that performs multiple attempts using various mechanisms for resolving the name, starting with a very strict mechanism, and proceeding sequentially through less strict mechanisms.

Method for operating a hearing device based on a speech signal, and hearing device

A method for operating a hearing device on the basis of a speech signal. An acousto-electric input transducer of the hearing device records a sound containing the speech signal from surroundings of the hearing device and converts the sound into an input audio signal. A signal processing operation generates an output audio signal based on the input audio signal. At least one articulatory and/or prosodic feature of the speech signal is quantitatively acquired through analysis of the input audio signal by way of the signal processing operation, and a quantitative measure of a speech quality of the speech signal is derived on the basis of the property. At least one parameter of the signal processing operation for generating the output audio signal based on the input audio signal is set on the basis of the quantitative measure of the speech quality of the speech signal.

METHOD FOR RATING THE SPEECH QUALITY OF A SPEECH SIGNAL BY WAY OF A HEARING DEVICE

A method for rating the speech quality of a speech signal by a hearing device. An acousto-electric input transducer records sound containing the speech signal and converts it into an input audio signal. At least one articulatory and/or prosodic property of the speech signal is quantitatively acquired through analysis of the input audio signal, and a quantitative measure of speech quality is derived based on the articulatory and/or prosodic property. A hearing device with an acousto-electric input transducer configured to record a sound and convert it into an input audio signal, and a signal processing apparatus that is designed to quantitatively acquire at least one articulatory and/or prosodic property of a component, contained in the input audio signal, of a speech signal based on analysis of the input audio signal and to derive a quantitative measure of the speech quality based on the at least one articulatory and/or prosodic property. 1. A method for rating a speech quality of a speech signal by a hearing device , the method comprising:recording a sound with an acousto-electric input transducer of the hearing device, the sound containing the speech signal from surroundings of the hearing device, and converting the sound into an input audio signal;quantitatively acquiring at least one articulatory property and/or prosodic feature of the speech signal through analysis of the input audio signal by a signal processing operation, andderiving a quantitative measure of the speech quality based on the at least one articulatory property and/or prosodic feature.2. The method according to claim 1 , the method further comprising acquiring claim 1 , as articulatory property of the speech signal claim 1 , at least one of:a characteristic variable correlated with the precision of predefined formants of vowels in the speech signal;a characteristic variable correlated with the dominance of consonants and/or fricatives in the speech signal; ora characteristic variable correlated ...

USER CALL QUALITY IMPROVEMENT

The disclosed system provides a facility for improving user call quality at a mobile device. The system includes an over-the-top (OTT) client that may be installed on the mobile device for allowing a user to initiate call quality tests. The system performs a call quality test to generate a call quality score or metric from the obtained audio sample via a Call Quality Algorithm. If the call quality score or metric falls below a predetermined threshold, the system may suggest (via the OTT client or via a push notification) that the user of the mobile device switch from the first communication interface (e.g., a radio network such as 4G) to a second communication interface (e.g., Wi-Fi) on the mobile device. The disclosed system tracks the call quality score or metric of multiple mobile devices operating within a telecommunications network, identifies service outages within the network, and notifies impacted mobile devices.

Methods and systems for enhancing pitch associated with an audio signal presented to a cochlear implant patient

An exemplary method of enhancing pitch of an audio signal presented to a cochlear implant patient includes 1) determining a frequency spectrum of an audio signal presented to a cochlear implant patient, the frequency spectrum comprising a plurality of frequency bins that each contain spectral energy, 2) generating a modified spectral envelope of the frequency spectrum of the audio signal, 3) identifying each frequency bin included in the plurality of frequency bins that contains spectral energy above the modified spectral envelope and each frequency bin included in the plurality of frequency bins that contains spectral energy below the modified spectral envelope, 4) enhancing the spectral energy contained in each frequency bin identified as containing spectral energy above the modified spectral envelope, and 5) compressing the spectral energy contained in each frequency bin identified as containing spectral energy below the modified spectral envelope. Corresponding methods and systems are also disclosed.

Speech/Dialog Enhancement Controlled by Pupillometry

The present disclosure relates to methods for processing a decoded audio signal and for selectively applying speech/dialog enhancement to the decoded audio signal. The present disclosure also relates to a method of operating a headset for computer-mediated reality. A method of processing a decoded audio signal comprises obtaining a measure of a cognitive load of a listener that listens to a rendering of the audio signal, determining whether speech/dialog enhancement shall be applied based on the obtained measure of the cognitive load, and performing speech/dialog enhancement based on the determination. A method of operating a headset for computer-mediated reality comprises obtaining eye-tracking data of a wearer of the headset, determining a measure of a cognitive load of the wearer of the headset based on the eye-tracking data, and outputting an indication of the cognitive load of the wearer of the headset. The present disclosure further relates to corresponding apparatus and systems, and to methods of operating such apparatus and systems.

METHODS AND APPARATUS FOR DECODING BASED ON SPEECH ENHANCEMENT METADATA

A method for hybrid speech enhancement which employs parametric-coded enhancement (or blend of parametric-coded and waveform-coded enhancement) under some signal conditions and waveform-coded enhancement (or a different blend of parametric-coded and waveform-coded enhancement) under other signal conditions. Other aspects are methods for generating a bitstream indicative of an audio program including speech and other content, such that hybrid speech enhancement can be performed on the program, a decoder including a buffer which stores at least one segment of an encoded audio bitstream generated by any embodiment of the inventive method, and a system or device (e.g., an encoder or decoder) configured (e.g., programmed) to perform any embodiment of the inventive method. At least some of speech enhancement operations are performed by a recipient audio decoder with Mid/Side speech enhancement metadata generated by an upstream audio encoder. 1. A method , comprising:receiving mixed audio content, wherein the mixed audio content includes at least a mid-channel mixed content signal and a side-channel mixed content signal, wherein the mid-channel signal represents a weighted or non-weighted sum of two channels of a reference audio channel representation, and wherein the side-channel signal represents a weighted or non-weighted difference of two channels of the reference audio channel representation;decoding, by an audio decoder, the mid-channel signal and the side-channel signal into a left channel signal and a right channel signal, wherein the decoding includes decoding based on speech enhancement metadata, wherein the speech enhancement metadata includes a preference flag which indicates at least a type of speech enhancement operation to be performed on the mid-channel signal and the side-channel signal during decoding, and wherein the speech enhancement metadata further indicates a first type of speech enhancement for the mid-channel signal and a second type of speech ...

System and Method for Auditing and Filtering Digital Audio Files

A computerized method for filtering a digital audio file to generate an output audio file that induces optimal health and cognitive ability in a listener of a playback of the output audio file is described herein. The method includes the steps of identifying a plurality of target frequencies that span within an octave, identifying a plurality of mid-point frequencies that are situated at mid-points between any two adjacent target frequencies, applying a peaking filter to the digital audio file centered around the plurality of mid-point frequencies to produce highest frequency attenuation at the plurality of mid-point frequencies, and generating the output audio file. 1. A computerized method for filtering a digital audio file to generate an output audio file that induces optimal health and cognitive ability in a listener of a playback of the output audio file , comprising:identifying a plurality of target frequencies that span within at least one octave;identifying a plurality of mid-point frequencies that are situated at mid-points between any two adjacent target frequencies;applying a set of peaking filters to the digital audio file centered around the plurality of mid-point frequencies to produce highest frequency attenuation at the plurality of mid-point frequencies; andgenerating the output audio file.2. The computerized method of claim 1 , wherein identifying a plurality of target frequencies comprises identifying a plurality of target frequencies that span more than one octave.3. The computerized method of claim 1 , wherein identifying a plurality of target frequencies comprises receiving a user input indicative of a number of target frequencies to be identified.4. The computerized method of claim 1 , wherein identifying a plurality of target frequencies comprises identifying seven target frequencies.5. The computerized method of claim 1 , wherein applying a set of peaking filters comprises applying five peaking filters of different bandwidths centered about ...

PLAYBACK ENHANCEMENT IN AUDIO SYSTEMS

Audio systems and methods are provided that enhance a portion of audio content relative to other portions of the audio content. The systems and methods select the portion to be enhanced and calculate an intelligibility metric of the selected portion, such as a dialogue portion. The systems and methods determine a gain based at least in part upon the intelligibility metric and apply the gain to the selected portion to provide an enhanced portion. The systems and methods provide an audio signal, based at least in part upon the enhanced portion, to an output for conversion to an acoustic signal, such as by an acoustic transducer. 1. An audio sound system , comprising:an input to receive input audio content;an output configured to provide an audio signal for conversion to acoustic signals in a listening environment; anda processor coupled to the input and to the output and configured to select a portion of the input audio content to be enhanced relative to other portions of the input audio content, to calculate an intelligibility metric of the selected portion, to determine a gain based at least in part upon the intelligibility metric, to apply the gain to the selected portion to provide an enhanced portion, to produce output audio content by combining the enhanced portion with the other portions of the input audio content, and to provide the output audio content to the output as the audio signal.2. The audio sound system of wherein the processor is further configured to select the portion of the input audio content as a dialogue portion and to calculate the intelligibility metric as a speech intelligibility metric of the selected dialogue portion relative to the other portions of the input audio content.3. The audio sound system of wherein the processor is further configured to select the portion of the input audio content as a dialogue portion based upon at least one of a center channel of the input audio content and a correlated portion of a left and right channel of ...

EFFICIENT DRC PROFILE TRANSMISSION

A method () for decoding an encoded audio signal () is described. The encoded audio signal () comprises a sequence of frames. Furthermore, the encoded audio signal () is indicative of a plurality of different dynamic range control (DRC) profiles for a corresponding plurality of different rendering modes. Different subsets of DRC profiles from the plurality of DRC profiles are comprised within different frames of the sequence of frames, such that two or more frames of the sequence of frames jointly comprise the plurality of DRC profiles. The method () comprises determining a first rendering mode from the plurality of different rendering modes; determining () one or more DRC profiles from a subset of DRC profiles comprised within a current frame of the sequence of frames; determining () whether at least one of the one or more DRC profiles is applicable to the first rendering mode; selecting () a default DRC profile as a current DRC profile, if none of the one or more DRC profiles is applicable to the first rendering mode; wherein definition data of the default DRC profile is known at a decoder () for decoding the encoded audio signal (); and decoding the current frame using the current DRC profile. 1. A method for decoding an encoded audio signal; wherein the encoded audio signal comprises a sequence of frames comprising encoded audio data and metadata , the metadata including a plurality of different sets of dynamic range control , referred to as DRC , gains , wherein the encoded audio signal further comprises an indication of a loudness of the audio signal , and DRC configuration metadata in one or more frames of the sequence of frames , wherein the DRC configuration metadata indicates a plurality of DRC profiles associated with the encoded audio signal , and , for each DRC profile , a range of output reference levels for which the DRC profile is applicable , wherein each set of DRC gains corresponds to one of the plurality of DRC profiles , the method comprising: ...

TRANSDUCER APPARATUS FOR HIGH SPEECH INTELLIGIBILITY IN NOISY ENVIRONMENTS

A transducer apparatus to provide high speech-intelligibility in a noisy environment. The transducer apparatus comprises a vibration-sensing transducer adapted to be placed on the non-honey and non-cartilaginous, i.e., fleshy, part of the head of the user—either on the all-flesh part of the cheek or all-flesh under chin. The vibrations sensed are vibrations arising from the user's voice in his mouth and conducted to the surface of the fleshy area of the users cheek or under-chin, and not by bone vibration. The embodiments of the invention include its application into headsets, earsets and helmets; and a switching means; and a means to realize a vibration transducer from an acoustical microphone. 1. A transducer apparatus comprising a transducer , whereinthe transducer is adapted to be placed on and to sense vibrations on the non-boney or non-cartilaginous part of the user's head, andthe vibrations arise from the user's voice.2. A transducer apparatus according to claim 1 , whereinthe non-boney part of the user's head is the fleshy area of the user's cheek near the mouth of the user, andthe vibrations are conducted to the surface of the fleshy area of the user's cheek through the flesh of the user's cheek.3. A transducer apparatus according to claim 1 , whereinthe transducer is an accelerometer, shock sensor, gyroscope, vibration microphone or vibration sensor.4. A transducer apparatus comprising a transducer claim 1 , whereinthe transducer is an acoustical-sensing microphone adapted to sense vibrations,the acoustical microphone having a housing,the housing having a hole that serves as the acoustical input port, andthe adaption of the acoustical microphone to sense vibrations is by means of the hole being placed on or pressed against the non-boney or non-cartilaginous part of said user's head.5. A transducer apparatus according to claim 4 , whereinthe hole is adapted to be covered by a membrane.6. A transducer apparatus according to claim 1 , whereinthe non-boney or ...

Method and System for Scaling Ducking of Speech-Relevant Channels in Multi-Channel Audio

A method and system for filtering a multi-channel audio signal having a speech channel and at least one non-speech channel, to improve intelligibility of speech determined by the signal. In typical embodiments, the method includes steps of determining at least one attenuation control value indicative of a measure of similarity between speech-related content determined by the speech channel and speech-related content determined by the non-speech channel, and attenuating the non-speech channel in response to the at least one attenuation control value. Typically, the attenuating step includes scaling of a raw attenuation control signal (e.g., a ducking gain control signal) for the non-speech channel in response to the at least one attenuation control value. Some embodiments are a general or special purpose processor programmed with software or firmware and/or otherwise configured to perform filtering in accordance the invention. 1. A method for filtering a multi-channel audio signal having a speech channel and at least one non-speech channel , to improve intelligibility of speech determined by the signal , said method including the steps of:(a) determining at least one attenuation control value indicative of a measure of similarity between speech-related content determined by the speech channel and speech-related content determined by at least one non-speech channel of the multi-channel audio signal, where the attenuation control value is generated based on at least one speech enhancement likelihood value for the non-speech channel, and the speech enhancement likelihood value is indicative of a likelihood that said at least one non-speech channel is indicative of content that enhances perceived quality of speech content determined by the speech channel; and(b) attenuating at least one non-speech channel of the multi-channel audio signal in response to the at least one attenuation control value.2. The method of claim 1 , wherein each attenuation control value determined ...

SELECTIVE ENFORCEMENT OF PRIVACY AND CONFIDENTIALITY FOR OPTIMIZATION OF VOICE APPLICATIONS

A computer-implemented method includes identifying a plurality of protected pieces from a conversation. The computer-implemented method further includes generating one or more confidence scores for each protected piece, wherein a confidence score is a degree of associativity between a protected piece and a type of sensitive information. The computer-implemented method further includes determining that the protected piece is associated with the type of sensitive information. The computer-implemented method further includes determining a type of protection action for each protected piece in the plurality of protected pieces. The computer-implemented method further includes performing the type of protection action for each protected piece in the plurality of protected pieces to form a modified conversation that is devoid of the sensitive information. A corresponding computer system and computer program product are also disclosed. 1. A computer-implemented method comprising:identifying a plurality of protected pieces from a conversation, wherein each protected piece in the plurality of protected pieces corresponds to a portion of the conversation that includes sensitive information;generating one or more confidence scores for each protected piece in the plurality of protected pieces, wherein a confidence score is a degree of associativity between a protected piece and a type of sensitive information;determining that the protected piece is associated with the type of sensitive information based, at least in part, on the confidence score exceeding a given threshold level;determining a type of protection action for each protected piece in the plurality of protected pieces based, at least in part, on the type of sensitive information associated with the protected piece; andperforming the type of protection action for each protected piece in the plurality of protected pieces to form a modified conversation, wherein the modified conversation is devoid of the sensitive ...

Voiceprint registration method, server and storage medium

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

Information processing apparatus and information processing method

A system that acquires first audio data including a voice command captured by a microphone; identifies second audio data included in broadcast content corresponding to a timing at which the first audio data is captured by the microphone; extracts the second audio data from the first audio data to generate third audio data; converts the third audio data to text data corresponding to the voice command; and outputs the text data.

Data Driven Radio Enhancement

Systems and methods are disclosed for data driven radio enhancement. For example, methods may include demodulating a radio signal to obtain a demodulated audio signal; determining a window of audio samples based on the demodulated audio signal; applying an audio enhancement network to the window of audio samples to obtain an enhanced audio segment, in which the audio enhancement network includes a machine learning network that has been trained using demodulated audio signals derived from radio signals; and storing, playing, or transmitting an enhanced audio signal based on the enhanced audio segment.

ELECTRONIC DEVICE AND OPERATION METHOD THEREOF

Provided are an electronic device and an operation method thereof. The operation method of an electronic device for processing an audio signal may include obtaining viewing environment information related to sound intelligibility, processing an input audio signal by separating the input audio signal into a first channel including a primary signal and a second channel including an ambient signal based on the viewing environment information, processing the input audio signal based on a frequency band and based on the viewing environment information, and generating an output signal based on processing the input audio signal. 1. An operation method of an electronic device for processing an audio signal , the operation method comprising:obtaining viewing environment information related to sound intelligibility;processing an input audio signal by separating the input audio signal into a first channel including a primary signal and a second channel including an ambient signal based on the viewing environment information;processing the input audio signal based on a frequency band and based on the viewing environment information; andgenerating an output signal based on processing the input audio signal.2. The operation method of claim 1 , wherein the viewing environment information includes at least one of information associated with ambient noise around the electronic device claim 1 , information associated with a space where the electronic device is located claim 1 , information associated with an ambient device around the electronic device claim 1 , and information associated with an installation environment of the electronic device.3. The operation method of claim 1 , wherein the processing the input audio signal by separating the input audio signal into the first channel including the primary signal and the second channel including the ambient signal comprises:determining weights for the primary signal and the ambient signal based on the viewing environment information; ...

Methods and systems for wireless audio

Various embodiments of the present technology comprise a method and system for wireless audio. In various embodiments, the system comprises a set of wirelessly connected ear buds, each ear bud suitable for placing in a human ear canal. Each ear bud comprises a microphone, an asynchronous sampling rate converter, a timer, and an audio clock. One ear bud from the set further comprises a control circuit and a synchronizer to synchronize the input of sound signals captured by the microphones and/or synchronize the processing and output of the sound signals.

Residual Noise Suppression

A method includes determining a preprocessed audio signal by removing some noise from an input audio signal. Here, portions of the preprocessed audio signal that include speech are separated by portions of the preprocessed audio signal that include residual noise. Additionally, the method includes determining an amplified signal by suppressing the preprocessed audio signal over the portions that include residual noise, and maintaining the preprocessed audio signal over the portions that include speech. 1. A method comprising:determining a preprocessed audio signal by removing some noise from an input audio signal, wherein portions of the preprocessed audio signal that include speech are separated by portions of the preprocessed audio signal that include residual noise; and suppressing the preprocessed audio signal over the portions that include residual noise, and', 'maintaining the preprocessed audio signal over the portions that include speech., 'determining an amplified signal by'}2. The method of claim 1 , further comprising:determining the portions of the preprocessed audio signal that include residual noise as corresponding to times when an envelope of the preprocessed audio signal is less than or equal to a first threshold signal; anddetermining the portions of the preprocessed signal that include speech as corresponding to times when the envelope of the preprocessed audio signal is larger than the first threshold signal.3. The method of claim 2 , wherein a value of the first threshold signal is in a range from 5% to 20% of a maximum value of the envelope of the preprocessed audio signal.4. The method of claim 2 , further comprising: a value equal to a maximum gain value for the portions of the preprocessed audio signal that include speech, and', 'at least one value smaller than the maximum gain value and larger than or equal to a threshold ratio for the portions of the preprocessed audio signal that include residual noise., 'setting a gain signal for ...

Playback sound provision device

A playback sound provision device includes: a surrounding information detection device configured to detect detection information including information on a three-dimensional object or a planar display around the vehicle; and a control device configured to determine a playback method for a playback sound based on a music piece based on the detection information when a predetermined target is included in the detection information, and provide the playback sound based on the playback method.

SELECTIVE ENFORCEMENT OF PRIVACY AND CONFIDENTIALITY FOR OPTIMIZATION OF VOICE APPLICATIONS

A computer-implemented method includes identifying a plurality of protected pieces from a conversation. The computer-implemented method further includes generating one or more confidence scores for each protected piece, wherein a confidence score is a degree of associativity between a protected piece and a type of sensitive information. The computer-implemented method further includes determining that the protected piece is associated with the type of sensitive information. The computer-implemented method further includes determining a type of protection action for each protected piece in the plurality of protected pieces. The computer-implemented method further includes performing the type of protection action for each protected piece in the plurality of protected pieces to form a modified conversation that is devoid of the sensitive information. A corresponding computer system and computer program product are also disclosed. 1. A computer-implemented method comprising:identifying a plurality of protected pieces from a conversation, wherein each protected piece in the plurality of protected pieces corresponds to a portion of the conversation that includes sensitive information;determining a type of protection action for each protected piece in the plurality of protected pieces based, at least in part, on the type of sensitive information associated with the protected piece; andperforming the type of protection action for each protected piece in the plurality of protected pieces to form a modified conversation, wherein the modified conversation is devoid of the sensitive information.2. The computer-implemented method of claim 1 , wherein determining the type of protection action for each protected piece in the plurality of protected pieces is further based on a type of medium in which the conversation is stored.3. The computer-implemented method of claim 1 , further comprising:requesting additional clarifying information about the protected piece based on a ...

PITCH EMPHASIS APPARATUS, METHOD AND PROGRAM FOR THE SAME

Provided is pitch enhancement processing having little unnaturalness even in time segments for consonants, and having little unnaturalness to listeners caused by discontinuities even when time segments for consonants and other time segments switch frequently. A pitch emphasis apparatus carries out the following as the pitch enhancement processing: for a time segment in which a spectral envelope of a signal has been determined to be flat, obtaining an output signal for each of times in the time segment, the output signal being a signal including a signal obtained by adding (1) a signal obtained by multiplying the signal of a time, further in the past than the time by a number of samples Tcorresponding to a pitch period of the time segment, a pitch gain σof the time segment, a predetermined constant B, and a value greater than 0 and less than 1, to (2) the signal of the time. 1. A pitch emphasis apparatus that obtains an output signal by executing pitch enhancement processing on each of time segments of a signal originating from an input audio signal , the apparatus comprising: [{'sub': 0', '0', '0, 'for a time segment in which a spectral envelope of the signal has been determined to be flat, obtaining an output signal for each of times in the time segment, the output signal being a signal including a signal obtained by adding (1) a signal obtained by multiplying the signal of a time, further in the past than the time by a number of samples Tcorresponding to a pitch period of the time segment, a pitch gain σof the time segment, a predetermined constant B, and a value greater than 0 and less than 1, to (2) the signal of the time, and'}, {'sub': 0', '0', '0, 'for a time segment in which a spectral envelope of the signal has been determined not to be flat, obtaining an output signal for each of times in the time segment, the output signal being a signal including a signal obtained by adding (1) a signal obtained by multiplying the signal of a time, further in the past ...

UTILIZATION OF LOCATION AND ENVIRONMENT TO IMPROVE RECOGNITION

A portable terminal has a network interface that receives a set of instructions having a sequence of at least one location and audio properties associated with the at least one location from a server. An audio circuit receives audio signals picked up by a microphone and processes the audio signals in a manner defined by the audio properties associated with the at least one location. A speech recognition module receives processed signals from the audio circuit and carries out a speech recognition process thereupon. 1. A device , comprising:a network interface that receives a set of instructions from a server, the instructions comprising at least one location where at least one action is to be carried out by a user and audio processing parameters comprising audio properties associated with the at least one location;an audio circuit that receives audio signals picked up by a microphone and processes the audio signals in a manner defined by the audio processing parameters comprising the audio properties associated with the at least one location, the audio processing parameters having been ascertained from the set of instructions; anda speech recognition module that receives processed signals from the audio circuit and carries out a speech recognition process thereupon.2. The device according to claim 1 , where audio signals picked up by the microphone are stored and conveyed to a server.3. The device according to claim 1 , where the speech recognition module utilizes a user template that characterizes speech of a particular user to enhance recognition accuracy.4. The device according to claim 1 , where the audio circuit comprises an amplifier and where the gain of the amplifier is set by the audio processing parameters comprising the audio properties for the at least one location.5. The device according to claim 1 , where the audio circuit comprises a noise comparison circuit that compares the audio with a noise model defined by the audio processing parameters ...

COMMUNICATION DEVICE AND SIDETONE VOLUME ADJUSTING METHOD THEREOF

A communication device and a sidetone volume adjusting method thereof are disclosed. The communication device includes a sound processor, a far-end sound receiver, a near-end sound receiver, a volume adjuster, and a sound player. The far-end sound receiver is configured to receive a far-end sound and transmit it to the sound processor. The near-end sound receiver is configured to receive a near-end sound such that the sound processor receives the near-end sound to form a sidetone. The volume adjustment module is configured to adjust the volume of the far-end sound and the sidetone to form the adjusted far-end sound and the adjusted sidetone, wherein the volume of the adjusted sidetone is based on the near-end sound and the adjusted far-end sound. The sound player is used to play the adjusted sidetone and the adjusted far-end sound.

Assistive listening system and method for television, radio & music systems

An assistive-listening system is used with sound-producing equipment that includes a signal source, and first and second sound sources operatively associated with the signal source and configured to produce sound corresponding to signals received from the signal source. The assistive-listening system includes a volume control operatively associated with the signal source and configured proportionally to change the volume of both the first and second sound sources. Also included is a support structure configured to support and position the second sound source so that a hearing-impaired listener may listen effectively to sound controlled by the volume control without disturbing normal-hearing listeners.

Spatial Audio Processing

According to an example embodiment, a technique for spatial audio processing including: determining at least one spatial parameter based, at least partially, on at least one input audio signal captured with at least one first device, configured to represent at least a portion of an audio scene; identifying a portion of interest of the audio scene based, at least partially, on the at least one spatial parameter; generating at least one first audio signal based, at least partially, on the at least one input audio signal; generating at least one second audio signal based, at least partially, on at least one audio signal captured with at least one second device; and combining, at least partially, the at least one first audio signal and the at least one second audio signal into at least one combined audio signal.

Automatic Calculation of Gains for Mixing Narration Into Pre-Recorded Content

A system and method of mixing narration into content. The system automatically reduces the volume of the content according to a threshold value and a knee value. In this manner, the audio of the content does not overwhelm the narration. 1. A method of automatically mixing first audio and second audio that are associated with video , the method comprising:receiving, by a mobile device, a user selection of a first content item, wherein the first content item has video data and first audio data, and wherein the first audio data is synchronized with the video data;outputting, by the mobile device, the video data and the first audio data;receiving, by the mobile device, second audio data from a microphone of the mobile device, wherein the second audio data is received contemporaneously with outputting the video data and the first audio data;calculating, by the mobile device, a loudness measure, wherein the loudness measure includes a loudness of the first audio data;attenuating, by the mobile device, the first audio data according to the loudness measure to form attenuated first audio data;mixing, by the mobile device, the attenuated first audio data and the second audio data to form a second content item, wherein the second content item has the video data, the attenuated first audio data, and the second audio data, and wherein the attenuated first audio data and the second audio data are synchronized with the video data; andstoring, by the mobile device, the second content item having been formed.2. The method of claim 1 , wherein the second audio data corresponds to narration by a user of the mobile device.3. The method of claim 1 , further comprising:receiving, by the mobile device, the video data and the first audio data, wherein the video data is received from a camera of the mobile device, and wherein the first audio data is received from a microphone of the mobile device; andstoring, by the mobile device, the video data and the first audio data as the first ...

CONFERENCING AUDIO MANIPULATION FOR INCLUSION AND ACCESSIBILITY

Various embodiments herein each include at least one of systems, methods, and software for conference audio manipulation for inclusion and accessibility. One embodiment, in the form of a method that may be performed, for example, on a server or a participant computing device. This method includes receiving a voice signal via a network and modifying an audible characteristic of the voice signal that is perceptible when the voice signal is audibly output. The method further includes outputting the voice signal including the modified audible characteristic. 1. A method comprising:receiving a voice signal via a network;selecting a speaker profile based on at least one of a property and content of the voice signal;modifying, based in part on the selected speaker profile, an audible characteristic of the voice signal that is perceptible when the voice signal is audibly output; andoutputting the voice signal including the modified audible characteristic.2. The method of claim 1 , wherein the audible characteristic of the voice signal is an audible frequency range.3. The method of claim 2 , wherein modifying the audible characteristic includes changing occurrences of the audible frequency range within the voice signal to a different audible frequency range based on a user setting.4. The method of claim 1 , wherein the speaker profile is selected based on processing of the audio signal by a speaker recognition process to obtain speaker identity data that is used to select the speaker profile.5. The method of claim 1 , wherein a speaker profile identifies at least one audible characteristic of the voice signal that is to be modified and how each of the at least one audible characteristics are to be modified.6. The method of claim 1 , wherein the modifying of the audible characteristic of the voice signal includes applying a filter to remove an audible portion of the voice signal.7. The method of claim 1 , further comprising:receiving user input that identifies the audible ...

RESPIRATOR MASK SPEECH ENHANCEMENT APPARATUS AND METHOD

Speech enhancement apparatus and respirator masks including speech enhancement apparatus, as well as methods of enhancing speech transmission for the wearer of a respirator mask are described herein. In one or more embodiments, the speech enhancement apparatus and methods described herein detect acoustic energy within a first frequency range in the clean air envelope of a respirator mask and deliver compensating acoustic energy outside of the clean air envelope using a speaker. The compensating acoustic energy is, in one or more embodiments, delivered in one or more predetermined attenuated frequency ranges that cover less than all of the detected first frequency range. In one or more embodiments, the compensating acoustic energy may be delivered with an attenuated amplitude profile that uniform or that is non-uniform over the one or more attenuated frequency ranges. 1. A respirator mask comprising:a mask body configured to define a clean air envelope between the mask and the mouth and nose of wearer; a microphone configured for attachment to the mask body, the microphone further configured to detect acoustic energy within the clean air envelope when attached to the mask body;', 'a speaker configured to produce acoustic energy outside of the clean air envelope;', receive a speech signal from the microphone, wherein the speech signal is indicative of acoustic energy detected by the microphone within a first frequency range; and', 'deliver an output signal to the speaker, wherein the output signal is configured to cause the speaker to emit compensating acoustic energy, wherein the compensating acoustic energy is emitted in one or more predetermined attenuated frequency ranges that cover less than all of the first frequency range, and wherein the compensating acoustic energy comprises a predetermined attenuated amplitude profile over each predetermined attenuated frequency range of the one or more predetermined attenuated frequency ranges., 'a controller operably ...

ENHANCING INTELLIGIBILITY OF SPEECH CONTENT IN AN AUDIO SIGNAL

Embodiments of the present invention relate to signal processing. Methods for enhancing intelligibility of speech content in an audio signal are disclosed. One of the methods comprises obtaining reference loudness of the audio signal. The method further comprises enhancing the intelligibility of the speech content by adjusting partial loudness of the audio signal based on the reference loudness and a degree of the intelligibility. Corresponding systems and computer program products are also disclosed. 1. A method for enhancing intelligibility of speech content in an audio signal , the speech content contained in a speech component of the audio signal , the method comprising:obtaining reference loudness of the audio signal; andenhancing the intelligibility of the speech content by adjusting partial loudness of the audio signal based on the reference loudness and a degree of the intelligibility.2. The method according to claim 1 , wherein adjusting the partial loudness of the audio signal comprises:increasing the partial loudness of the speech component based on the reference loudness and the degree of the intelligibility.3. The method according to claim 1 , wherein adjusting the partial loudness of the audio signal comprises:in response to a determination that the audio signal contains a non-speech component, reducing the partial loudness of the non-speech component based on the reference loudness and the degree of the intelligibility.4. The method according to claim 1 , wherein enhancing the intelligibility of the speech content by adjusting the partial loudness of the audio signal comprises:adjusting the partial loudness of the audio signal to the reference loudness;determining whether an intelligibility criterion is met by the intelligibility of the speech content in the adjusted audio signal;determining target loudness in response to the intelligibility criterion being not met; and adjusting the partial loudness of the audio signal to the target loudness.5. The ...

METHOD AND APPARATUS FOR PROCESSING AN AUDIO SIGNAL, AUDIO DECODER, AND AUDIO ENCODER

A method is described that processes an audio signal. A discontinuity between a filtered past frame and a filtered current frame of the audio signal is removed using linear predictive filtering. 1. A method for processing an audio signal , the method comprising:removing a discontinuity between a filtered past frame and a filtered current frame of the audio signal using linear predictive filtering.2. The method of claim 1 , comprising filtering the current frame of the audio signal and removing the discontinuity by modifying a beginning portion of the filtered current frame by a signal acquired by linear predictive filtering a predefined signal with initial states of the linear predictive filter defined on the basis of a last part of the past frame.3. The method of claim 2 , wherein the initial states of the linear predictive filter are defined on the basis of a last part of the unfiltered past frame filtered using the set of filter parameters for filtering the current frame.4. The method of claim 1 , further comprising estimating the linear predictive filter on the filtered or non-filtered audio signal.5. The method of claim 4 , wherein estimating the linear predictive filter comprises estimating the filter based on the past and/or current frame of the audio signal or based on the past filtered frame of the audio signal using the Levinson-Durbin algorithm.6. The method of claim 1 , wherein the linear predictive filter comprises a linear predictive filter of an audio codec.7. The method of claim 1 , wherein removing the discontinuity comprises processing the beginning portion of the filtered current frame claim 1 , wherein the beginning portion of the current frame comprises a predefined number of samples being less or equal than the total number of samples in the current frame claim 1 , and wherein processing the beginning portion of the current frame comprises subtracting a beginning portion of a zero-input-response (ZIR) from the beginning portion of the filtered ...

VEHICLE AUDIO TRANSMISSION CONTROL

Methods and systems for controlling audio communications between occupants of a vehicle are provided. In accordance with one embodiment, a system includes an interface and a processor. The interface is configured to at least facilitate receiving a request for sound transmission from a first occupant inside a vehicle to a second occupant inside the vehicle. The processor is coupled to the interface, and is configured to at least facilitate identifying respective locations of the first occupant and the second occupant, and performing the sound transmission with an adjustment for a phase difference based at least in part on the respective locations of the first occupant and the second occupant. 1. A method comprising:receiving a request for sound transmission from a first occupant inside a vehicle to a second occupant inside the vehicle;identifying respective locations of the first occupant and the second occupant;adjusting for a phase difference between a transmitted sound from the first occupant and a reflected sound from the first occupant, wherein the adjusting for the phase difference is made based at least in part on the respective locations of the first occupant and the second occupant andperforming the sound transmission with the adjustment for the phase difference, wherein the step of performing the sound transmission comprises provided the sound transmission of an amplified sound from the first occupant via an audio speaker that is disposed inside the vehicle proximate to the second occupant, and wherein the adjustment adjusts for a latency between the amplified sound and the reflected sound.23.-. (canceled)4. The method of claim 1 , wherein the adjustment adjusts for a latency between the amplified sound and the reflected sound.5. The method of claim 4 , further comprising:determining a distance between the first occupant and the second occupant; anddetermining the latency using the distance.6. The method of claim 5 , wherein the step of determining the ...

Audio Signal Processing

An estimated system gain spectrum of an acoustic system is generated, and updated in real-time to respond to changes in the acoustic system. Peak gains in the estimated system gain spectrum are tracked as the estimated system gain spectrum is updated. Based on the tracking, at least one frequency at which the estimated system gain spectrum is currently exhibiting a peak gain is identified. Based on the identification of the at least one frequency, an audio equalizer is controlled to apply, to a first speech containing signal to be played out via an audio output device of the audio device and/or to a second speech containing signal received via an audio input device of the audio device, an equalization filter to reduce the level of that signal at the identified frequency. The equalization filter is applied continuously throughout intervals of both speech activity and speech inactivity in that signal.

SYSTEMS, METHODS, AND DEVICES FOR INTELLIGENT SPEECH RECOGNITION AND PROCESSING

Systems, methods, and devices for intelligent speech recognition and processing are disclosed. According to one embodiment, a method for improving intelligibility of a speech signal may include (1) at least one processor receiving an incoming speech signal comprising a plurality of sound elements; (2) the at least one processor recognizing a sound element in the incoming speech signal to improve the intelligibility thereof; (3) the at least one processor processing the sound element by at least one of modifying and replacing the sound element; and (4) the at least one processor outputting the processed speech signal comprising the processed sound element. 1. A method for improving intelligibility of a speech signal , comprising:at least one processor receiving an incoming speech signal comprising a plurality of sound elements;the at least one processor recognizing a sound element in the incoming speech signal to improve the intelligibility thereof;the at least one processor processing the sound element by at least one of modifying and replacing the sound element; andthe at least one processor outputting the processed speech signal comprising the processed sound element.2. The method of claim 1 , wherein the sound element comprises at least one of a continuant sound element and a non-continuant sound element.3. The method of claim 1 , wherein the processing increases a duration of the sound element.4. The method of claim 1 , wherein the processing decreases a duration of the sound element.5. The method of claim 1 , further comprising:the at least one processor recognizing a second sound element in the incoming speech signal to improve the intelligibility thereof; andthe at least one processor processing the second sound element by at least one of modifying and replacing the sound element;wherein the second sound element is modified or replaced to compensate for the processing of the first sound element.6. The method of claim 1 , wherein the sound element is a speech ...

Voice converting apparatus and method for converting user voice thereof

A voice converting apparatus and a voice converting method are provided. The method of converting a voice using a voice converting apparatus including receiving a voice from a counterpart, analyzing the voice and determining whether the voice abnormal, converting the voice into a normal voice by adjusting a harmonic signal of the voice in response to determining that the voice is abnormal, and transmitting the normal voice.

APPARATUS AND METHOD FOR POWER EFFICIENT SIGNAL CONDITIONING FOR A VOICE RECOGNITION SYSTEM

A disclosed method includes monitoring an audio signal energy level while having a noise suppressor deactivated to conserve battery power, buffering the audio signal in response to a detected increase in the audio energy level, activating and running a voice activity detector on the audio signal in response to the detected increase in the audio energy level and activating and running a noise estimator in response to voice being detected in the audio signal by the voice activity detector. The method may further include activating and running the noise suppressor only if the noise estimator determines that noise suppression is required. The method activates and runs a noise type classifier to determine the noise type based on information received from the noise estimator and selects a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient. 1. A computer-implemented method when executed on data processing hardware of a computing device causes the data processing hardware to perform operations comprising:receiving an audio signal detected by a first microphone in a group of microphones of the computing device while a second microphone in the group of microphones is powered off;while the second microphone is powered off, determining an audio signal energy level of the audio signal detected by the first microphone has deviated from a baseline audio signal energy level by more than a threshold amount; andin response to determining that the audio signal energy level of the audio signal detected by the first microphone has deviated from the baseline audio signal energy level by more than the threshold amount, triggering the second microphone to power on.2. The computer-implemented method of claim 1 , wherein the operations further comprise claim 1 , in response to determining the audio signal energy level of the audio signal detected by the first microphone has ...

Speech communication system for combined voice recognition, hands-free telephony and in-car communication

A multi-mode speech communication system is described that has different operating modes for different speech applications. A speech service compartment contains multiple system users, multiple input microphones that develop microphone input signals from the system users to the system, and multiple output loudspeakers that develop loudspeaker output signals from the system to the system users. A signal processing module is in communication with the speech applications and includes an input processing module and an output processing module. The input processing module processes the microphone input signals to produce a set user input signals for each speech application that are limited to currently active system users for that speech application. The output processing module processes application output communications from the speech applications to produce loudspeaker output signals to the system users, wherein for each different speech application, the loudspeaker output signals are directed only to system users currently active in that speech application. The signal processing module dynamically controls the processing of the microphone input signals and the loudspeaker output signals to respond to changes in currently active system users for each application.

METHOD AND SYSTEM FOR ADJUSTING USER SPEECH IN A COMMUNICATION SESSION

A system that incorporates the subject disclosure may include, for example, receive user speech captured at a second end user device during a communication session between the second end user device and a first end user device, apply speech recognition to the user speech, identify an unclear word in the user speech based on the speech recognition, adjust the user speech to generate adjusted user speech by replacing all or a portion of the unclear word with replacement audio content, and provide the adjusted user speech to the first end user device during the communication session. Other embodiments are disclosed. 1. A method , comprising:detecting, by a processing system including a processor, a communication session between a first user and a second user;receiving, by the processing system, user input from the first user, wherein the user input is sent from a first communication device;determining, by the processing system, an impairment of the first user responsive to analyzing, by the processing system, the user input from the first user;modifying, by the processing system, the user input according to a group of adjustment techniques resulting in modified user input responsive to determining the impairment; andproviding, by the processing system, the modified user input to a second communication device, wherein the second communication device is associated with the second user.2. The method of claim 1 , wherein the determining of the impairment of the first user comprises:accessing, by the processing system, a first user profile for the first user; anddetermining, by the processing system, the impairment of the first user according to the first user profile.3. The method of claim 1 , wherein the determining of the impairment of the first user comprises:monitoring, by the processing system, previous communications of the first user resulting in monitored previous communications; anddetermining, by the processing system, the impairment of the first user according ...

Information processing apparatus and information processing method

[Object] To more flexibly control the affinity of a spoken utterance for a background sound in accordance with the importance degree of an information notification. [Solution] There is provided an information processing apparatus including an utterance control unit that controls an output of a spoken utterance corresponding to notification information. The utterance control unit controls an output mode of the spoken utterance on the basis of an importance degree of the notification information and affinity for a background sound. In addition, there is provided an information processing method including controlling, by a processor, an output of a spoken utterance corresponding to notification information. The controlling further includes controlling an output mode of the spoken utterance on the basis of an importance degree of the notification information and affinity for a background sound.

AUDIO SIGNAL PROCESSING METHOD, APPARATUS AND DEVICE, AND STORAGE MEDIUM

An electronic device obtains audio signals collected by different microphones in a microphone array. The device filters the audio signals using a first filter to obtain a first target beam. The first filter is configured to suppress an interference speech in the audio signals and enhance a target speech in the audio signals. The device filters the audio signals using a second filter to obtain a first interference beam. The second filter is configured to suppress the target speech and enhance the interference speech. The device a second interference beam of the first interference beam using a third filter. The device determines a difference between the first target beam and the second interference beam as a first audio processing output. The device adaptively updates at least one of the second filter and the third filter, and updates the first filter according to the updated second filter and/or third filter. 1. An audio signal processing method performed by an electronic device , the method comprising:obtaining audio signals collected by different microphones in a microphone array;filtering the audio signals using a first filter to obtain a first target beam, wherein the first filter is configured to suppress an interference speech in the audio signals and enhance a target speech in the audio signals;filtering the audio signals using a second filter to obtain a first interference beam, wherein the second filter is configured to suppress the target speech and enhance the interference speech;obtaining a second interference beam of the first interference beam using a third filter, wherein the third filter is configured to perform a weighted adjustment on the first interference beam;determining a difference between the first target beam and the second interference beam as a first audio processing output; andadaptively updating at least one of the second filter and the third filter; andupdating the first filter according to the updated second filter and/or third filter.2 ...

EVALUATION APPARATUS, TRAINING APPARATUS, METHODS AND PROGRAMS FOR THE SAME

An evaluation device applies a lowpass filter with a cutoff frequency being a first predetermined value or a second predetermined value greater than the first predetermined value with or without change of feedback formant frequencies which are formant frequencies of a picked-up speech signal, converts the picked-up speech signal, feeds back the converted speech signal to a subject, and includes an evaluation unit that calculates a compensatory response vector by using pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted with change of the feedback formant frequencies to the subject, and pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted without change of the feedback formant frequencies to the subject, and determines an evaluation based on a compensatory response vector for each cutoff frequency. 1. An evaluation device comprising:a signal analyzer configured to analyze a picked-up speech signal, and determine a first formant frequency and a second formant frequency;a convertor configured to apply a lowpass filter with a cutoff frequency being a first predetermined value or a second predetermined value greater than the first predetermined value with or without change of feedback formant frequencies which are formant frequencies of the picked-up speech signal, and convert the picked-up speech signal;a feedback feeder configured to feed back the converted speech signal to a subject; andan evaluator configured to determine a compensatory response vector by using pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted with change of the feedback formant frequencies ...

Audio Signal

A computer device () for processing audio signals is described. The computer device () includes at least a processor and a memory. The computer device () is configured to receive a bitstream comprising a combined audio signal, the combined audio signal comprising a first audio signal including speech and a second audio signal. The computer device () is configured to compress the combined audio signal to provide a compressed audio signal. The computer device () is configured to control a dynamic range of the compressed audio signal to provide an output audio signal. In this way, a quality of the speech included in the output audio signal is improved. 1. A computer device for processing audio signals , the computer device including at least a processor and a memory , wherein the computer device is configured to:receive a bitstream comprising a combined audio signal, the combined audio signal comprising a first audio signal including speech and a second audio signal;compress the combined audio signal to provide a compressed audio signal; andcontrol a dynamic range of the compressed audio signal to provide an output audio signal;whereby a quality of the speech included in the output audio signal is improved.2. The computer device according to claim 1 , wherein the computer device is configured to compress the combined audio signal by selectively reducing an amplitude of the second audio signal.3. The computer device according to any previous claim claim 1 , wherein the computer device is configured to compress the combined audio signal by selectively increasing an amplitude of the speech included in the first audio signal.4. The computer device according to any previous claim claim 1 , wherein the computer device is configured to compress the combined audio signal by matching amplitudes of the first audio signal and the second audio signal.5. The computer device according to any previous claim claim 1 , wherein the computer device is configured to:selectively ...

Method and Device for Processing Sound Signal for Communications Device

A method and a device for processing a sound signal for a communications device, where a relationship between values of a volume of a first sound signal collected by a main microphone and a volume of a second sound signal collected by an auxiliary microphone is acquired by comparison, to determine a sound signal processing policy, and according to the sound signal processing policy, a sound signal to be sent to a peer communications terminal is determined, where the sound signal processing policy is used to ensure that a volume of the sound signal to be sent to the peer communications terminal exceeds a preset volume threshold. 1. A method for processing a sound signal for a communications device , comprising:acquiring a first sound signal collected by a main microphone and a second sound signal collected by an auxiliary microphone;determining a sound signal processing policy according to a relationship between values of a volume of the first sound signal and a volume of the second sound signal; anddetermining, according to the sound signal processing policy, a sound signal to be sent to a peer communications terminal, wherein the sound signal processing policy ensures a volume of the sound signal to be sent to the peer communications terminal exceeds a preset volume threshold.2. The method according to claim 1 , wherein the sound signal processing policy comprises a first sound signal processing policy claim 1 , wherein determining the sound signal processing policy comprises determining that the sound signal processing policy is the first sound signal processing policy when the volume of the first sound signal is less than the volume of the second sound signal claim 1 , wherein the first sound signal processing policy comprises determining whether the volume of the second sound signal is greater than or equal to the preset volume threshold claim 1 , and wherein determining the sound signal to be sent to the peer communications terminal comprises:sending the second ...

ENHANCEMENT OF AUDIO CAPTURED BY MULTIPLE MICROPHONES AT UNSPECIFIED POSITIONS

Embodiments disclosed herein provide systems, methods, and computer readable media for steering a camera and enhancing audio captured by microphones at unspecified positions. In a particular embodiment, a method provides receiving audio captured by the plurality of microphones at a location and receiving video captured of a scene that includes the plurality of microphones captured by a first camera at a first camera position. The method further provides identifying the plurality of microphones in the scene and determining physical positions of the plurality of microphones at the location relative to the first camera position. The method then provides adjusting the audio based on the physical positions of the plurality of microphones. 1. A method of determining positions of a plurality of microphones , the method comprising:receiving audio captured by the plurality of microphones at a location;receiving video captured of a scene that includes the plurality of microphones captured by a first camera at a first camera position;identifying the plurality of microphones in the scene;determining physical positions of the plurality of microphones at the location relative to the first camera position; andadjusting the audio based on the physical positions of the plurality of microphones.2. The method of claim 1 , further comprising:identifying a speaker in the audio;determining a first physical position of the speaker based on the physical positions of the plurality of microphones; andadjusting a video camera to feature the first physical position.3. The method of claim 2 , wherein determining a first physical position of the speaker comprises:determining a time difference between when each of the plurality of microphones captured a portion of the audio from the speaker.4. The method of claim 1 , wherein identifying the plurality of microphones comprises:performing image recognition on the video to identify each microphone of the plurality of microphones.5. The method of ...

Respirator mask speech enhancement apparatus and method

Speech enhancement apparatus and respirator masks including speech enhancement apparatus, as well as methods of enhancing speech transmission for the wearer of a respirator mask are described herein. In one or more embodiments, the speech enhancement apparatus and methods described herein detect acoustic energy within a first frequency range in the clean air envelope of a respirator mask and deliver compensating acoustic energy outside of the clean air envelope using a speaker. The compensating acoustic energy, in one or more embodiments, exhibits a predetermined attenuated amplitude profile such that the compensating acoustic energy has an amplitude less than 6 dB greater than the acoustic attenuation profile of the mask body over at least 90% of a predetermined attenuated frequency range.

Playback enhancement in audio systems

Audio systems and methods are provided that enhance a portion of audio content relative to other portions of the audio content. The systems and methods select the portion to be enhanced and calculate an intelligibility metric of the selected portion, such as a dialogue portion. The systems and methods determine a gain based at least in part upon the intelligibility metric and apply the gain to the selected portion to provide an enhanced portion. The systems and methods provide an audio signal, based at least in part upon the enhanced portion, to an output for conversion to an acoustic signal, such as by an acoustic transducer.

NOISE ADAPTIVE POST FILTERING

An apparatus comprising at least one processor and at least one memory including computer code for one or more programs, the at least one memory and the computer code configured to with the at least one processor to cause the apparatus to at least perform: estimating a signal to noise ratio value for an audio signal; generating a post-filter comprising at least one of: a first formant frequency filter and a second formant frequency filter, wherein the post-filter is dependent on the signal to noise ratio value for the audio signal, 130-. (canceled)31. A method comprising:estimating a signal to noise ratio value for an audio signal;generating a post-filter comprising at least one of: a first formant frequency filter and a second formant frequency filter, wherein the post-filter is dependent on the signal to noise ratio value for the audio signal.32. The method as claimed in claim 31 , wherein the post-filter is configured to move energy of the audio signal to higher frequencies.33. The method as claimed in claim 31 , wherein when generating the post-filter comprising the first formant frequency filter claim 31 , further comprises generating a first formant frequency parameter configured to attenuate first formant frequency components of the audio signal dependent on the signal to noise ratio value for the audio signal.34. The method as claimed in claim 33 , wherein generating the first formant frequency parameter dependent on the signal to noise ratio value for the audio signal comprises:comparing the signal to noise ratio value for the audio signal against a first signal to noise ratio threshold value;generating a maximum post-filter first formant frequency parameter value dependent on the signal to noise ratio value for the audio signal being greater than the signal to noise ratio threshold value; andgenerating a second post-filter formant frequency parameter value dependent on the signal to noise ratio value for the audio signal being less than the signal to noise ...

Smartphone bluetooth headset receiver

Systems and methods are provided for allowing a user with a Smartphone to pair the Smartphone with another Bluetooth device to receive audio that is played to the user over headphones or through speakers on the Smartphone. Further, an audio processing module is used to modify the audio presented to the user, extract closed captioning text to be displayed to the user, find information relevant to the audio to be displayed to the user, and pause audio content sent to the Smartphone when phone calls or other Smartphone interruptions occur.

PERSONALIZED, REAL-TIME AUDIO PROCESSING

An apparatus and method for real-time audio processing employs a gaze detection sensor to detect a direction of a user's gaze and output a gaze signal corresponding to the detected direction of the user's gaze. A digital signal processing unit responds to a plurality of signals corresponding to a plurality of sounds received at the apparatus, and the determined direction of gaze to identify a signal of interest from the plurality of signals using the gaze signal. The signal of interest is processed for output to the user. In embodiments, a microphone array provides the plurality of signals. An imaging sensor may work with either the microphone array or the gaze detection sensor to identify the signal of interest. 1. (canceled)2. A computer-implemented method performed by a user wearable device , the method comprising:detecting a direction of a gaze of a user based at least in part on monitoring user head motion;identifying, in an electronic data storage, one or more available actions that correspond to the direction of the gaze of the user;selecting a first action from one or more available actions based at least in part on the direction of the gaze of the user; andexecuting a set of computer-readable instructions that correspond to the first action.3. The method of claim 2 , wherein detecting the direction of the gaze of the user comprises:detecting the direction of the gaze of the user based at least in part on monitoring a position of an eye of the user.4. The method of claim 2 , wherein detecting the direction of the gaze of the user comprises:detecting the direction of the gaze of the user based at least in part on an image.5. The method of claim 2 , wherein selecting the first action from the one or more available actions comprises:selecting to adjust playback of audio, video, or both, based at least in part on the direction of the gaze of the user.6. The method of claim 2 , wherein selecting the first action from the one or more available actions comprises: ...

Method of enhancing speech using variable power budget

Disclosed herein is a method of enhancing speech. The method includes calculating a far-end speech spectrum by performing fast Fourier transformation of a signal received by a far-end user, calculating a background noise spectrum collected by a microphone provided to a mobile device of a near-end user; calculating a gain from the far-end speech spectrum and the background noise spectrum using a speech intelligibility index-based module, and deriving an enhanced far-end speech spectrum by applying the gain to the far-end speech spectrum, wherein, in calculating a gain using a speech intelligibility index-based module, a power budget used for transmitting and receiving a speech signal is set to vary with the background noise spectrum.

METHOD FOR DENOISING VOICE DATA, DEVICE, AND STORAGE MEDIUM

The present disclosure provides a method for denoising voice data, an electronic device, and a computer readable storage medium. The present disclosure relates to the technical field of artificial intelligence, such as Internet of Vehicles, smart cockpit, smart voice, and voice recognition. A specific embodiment of the method includes: receiving an input to-be-played first piece of voice data; and invoking, in response to not detecting a synthetic voice interruption signal in a process of playing the first piece of voice data, a preset first denoising algorithm to filter out noise data except for the first piece of voice data. 1. A method for denoising voice data , comprising:receiving an input to-be-played first piece of voice data; andinvoking, in response to not detecting a synthetic voice interruption signal in a process of playing the first piece of voice data, a preset first denoising algorithm to filter out noise data except for the first piece of voice data.2. The method according to claim 1 , wherein the method further comprises:receiving, in response to detecting the synthetic voice interruption signal in the process of playing the first piece of voice data, an input second piece of voice data based on the synthetic voice interruption signal, and invoking a preset second denoising algorithm to filter out voice data except for human voice data from the second piece of voice data.3. The method according to claim 1 , wherein the invoking the preset first denoising algorithm to filter out the noise data except for the first piece of voice data comprises:identifying in-vehicle regular noises based on a preset in-vehicle regular noise feature set; andremoving an in-vehicle regular noise mixedly played with the first piece of voice data.4. The method according to claim 2 , wherein the invoking the preset second denoising algorithm to filter out the voice data except for the human voice data in the second piece of voice data comprises:identifying in-vehicle ...

Speech Synthesis Device and Method

This invention is an improvement of technology for automatically generating response voice to voice uttered by a speaker (user), and is characterized by controlling a pitch of the response voice in accordance with a pitch of the speaker's utterance. A voice signal of the speaker's utterance (e.g., question) is received, and a pitch (e.g., highest pitch) of a representative portion of the utterance is detected. Voice data of a responsive to the utterance is acquired, and a pitch (e.g., average pitch) based on the acquired response voice data is acquired. A pitch shift amount for shifting the acquired pitch to a target pitch having a particular relationship to the pitch of the representative portion is determined. When response voice is to be synthesized on the basis of the response voice data, the pitch of the response voice to be synthesized is shifted in accordance with the pitch shift amount. 1. A speech synthesis method comprising:receiving a voice signal of an utterance;detecting a voiced section of the voice signal;detecting a pitch of a trailing end portion of the voiced section; [0030]acquiring voice data of a response to the utterance;acquiring a representative pitch based on the voice data of the response;determining one shift amount for shifting the representative pitch to a target pitch having a particular relationship to the detected pitch of the trailing end portion; andsynthesizing voice of the response based on the voice data of the response, while shifting pitch of the voice data in accordance with the one shift amount.2. The speech synthesis method as claimed in claim 1 , wherein the voiced section of the voice signal is a portion where a pitch of the voice signal is detectable. [0029]3. The speech synthesis method as claimed in claim 1 , wherein the trailing end portion is a part of the voiced section. [0030]4. The speech synthesis method as claimed in claim 1 , wherein the trailing end portion has a predetermined time width. [0030]5. The speech ...

Method and Device for Recognizing State of Meridian

The present application relates to a method and device for recognizing the state of a human body meridian by utilizing a voice recognition technology, the method comprising: receiving an input voice of a user; preprocessing the input voice; extracting a stable feature of the preprocessed input voice; primarily classifying the stable feature on the basis of a feature recognition model, and determining a basic classification pitch, wherein the basic classification pitch comprises Gong, Shang, Jue, Zhi and Yu (respectively equivalent to do, re, mi, sol and la); secondarily classifying the stable feature on the basis of the feature recognition model, and determining a secondary classification tone in the basic classification pitch; and recognizing the state of a meridian according to the secondary classification tone. The method for recognizing the state of a human body meridian of the present invention can accurately recognize the state of a human body meridian by classifying individual voices, thus solving the problem that conventional voice recognition and classification are completely dependent on human experience.

PROCESSING SPOKEN COMMANDS TO CONTROL DISTRIBUTED AUDIO OUTPUTS

A system that is capable of controlling multiple entertainment systems and/or speakers using voice commands. The system receives voice commands and may determine audio sources and speakers indicated by the voice commands. The system may generate audio data from the audio sources and may send the audio data to the speakers using multiple interfaces. For example, the system may send the audio data directly to the speakers using a network address, may send the audio data to the speakers via a voice-enabled device or may send the audio data to the speakers via a speaker controller. The system may generate output zones including multiple speakers and may associate input devices with speakers within the output zones. For example, the system may receive a voice command from an input device in an output zone and may reduce output audio generated by speakers in the output zone. 120.-. (canceled)21. A computer-implemented method comprising:detecting, by an input device in a first environment, input audio corresponding to an utterance;determining an output device causing first audio to be output in the first environment; andbased at least in part on detecting the input audio, sending, to a networking component associated with the output device, an override command to reduce a volume of the first audio.22. The computer-implemented method of claim 21 , further comprising:outputting, by the input device, second audio in the first environment; andbased at least in part on detecting the input audio, reducing a volume of the second audio.23. The computer-implemented method of claim 21 , wherein the input device is paired with the output device using a wireless connection.24. The computer-implemented method of claim 21 , further comprising:determining an identifier corresponding to the output device,wherein sending the override command is further based at least in part on the identifier.25. The computer-implemented method of claim 21 , further comprising:determining that the output ...

METHOD AND APPARATUS FOR DISCRIMINATING BETWEEN VOICE SIGNALS

A method and apparatus for distinguishing voice signals that are played together over the same speaker employs spectral reshaping of one or more of the audio signals. The spectral reshaping shifts modifies the timber of the voice signal while not modifying the pitch of the voice signal. Additional techniques can be used to further distinguish voice signals, such as dynamic gain offset and frequency shifting. After processing one or more signals to spectrally reshape them, they can be played over the same speaker. A user hearing the resulting acoustic signal will be more able to distinguish between the multiple voice signals being played. 1. A method for differentiating audio signals when played together over a speaker , comprising:receiving, at the same time, a primary audio signal on a primary channel and a secondary audio signal on a secondary channel;spectrally reshaping at least one of the primary audio signal and the secondary audio signal based on spectral content of the other audio signal to produce resulting signals including at least one reshaped signal;mixing the resulting signals; andplaying the resulting signals over the speaker.2. The method of claim 1 , wherein spectrally reshaping is performed in response to detecting voice content in the primary audio signal.3. The method of claim 1 , further comprising adjusting a gain of at least one of the resulting signals to maintain a preselected gain offset between the resulting signals.4. The method of claim 3 , wherein the preselected gain is based on the instantaneous energy of the primary audio signal.5. The method of claim 1 , wherein spectrally reshaping is performed continuously based on spectral comparison of the spectral content of the primary and secondary audio signals.6. The method of claim 1 , wherein spectrally reshaping is performed by calculating an energy level in each of a plurality of sub-bands of the primary and secondary audio signals and applying a dynamic equalization adjustment to at ...

ADAPTIVE SPEECH INTELLIGIBILITY CONTROL FOR SPEECH PRIVACY

In some examples, adaptive speech intelligibility control for speech privacy may include determining, based on background noise at a near-end of a speaker, a noise estimate associated with speech emitted from the speaker, and comparing, by using a specified factor, the noise estimate to a speech level estimate for the speech emitted from the speaker. Adaptive speech intelligibility control for speech privacy may further include determining, based on the comparison, a gain value to be applied to the speaker to produce the speech at a specified level to maintain on-axis intelligibility with respect to the speaker, and applying the gain value to the speaker. 1. An adaptive speech intelligibility control for speech privacy apparatus comprising:a processor; and determine, based on background noise at a near-end of a speaker, a noise estimate associated with speech emitted from the speaker;', 'compare, by using a specified factor, the noise estimate to a speech level estimate for the speech emitted from the speaker;', 'determine, based on the comparison, a gain value to be applied to the speaker to produce the speech at a specified level to maintain on-axis intelligibility with respect to the speaker; and', 'apply the gain value to the speaker., 'a memory storing machine readable instructions that when executed by the processor cause the processor to2. The apparatus according to claim 1 , wherein the speaker includes an ultrasonic modulator to modulate the speech claim 1 , and a piezo-transducer to receive the modulated speech and to generate a directional audio wavefront for a target listener at a specified location.3. The apparatus according to claim 1 , wherein the machine readable instructions to determine claim 1 , based on the background noise at the near-end of the speaker claim 1 , the noise estimate associated with the speech emitted from the speaker further comprise machine readable instructions to cause the processor to:determine, based on the background noise ...

FREQUENCY EXTRACTION METHOD USING DJ TRANSFORM

A method, of which each step is performed by a computer, for extracting a frequency of an input sound according to an embodiment of the present disclosure comprises the steps of: modeling a plurality of springs which have natural frequencies different from each other and oscillate according to an input sound; calculating transient-state-pure-tone amplitudes of the plurality of modeled springs; calculating expected steady-state amplitudes of the plurality of modeled springs; calculating predicted pure-tone amplitudes based on the expected steady-state amplitudes; calculating filtered pure-tone amplitudes by multiplying the transient-state-pure-tone amplitudes with the predicted pure-tone amplitudes ; and extracting the natural frequency of the spring which corresponds to a local maximum value among the filtered pure-tone amplitudes. 1. A method , of which each step is performed by a computer , for extracting a frequency of an input sound comprising the steps of:modeling a plurality of springs which have natural frequencies different from each other and oscillate according to an input sound;calculating transient-state-pure-tone amplitudes of the plurality of modeled springs;calculating expected steady-state amplitudes of the plurality of modeled springs;calculating predicted pure-tone amplitudes based on the expected steady-state amplitudes;calculating filtered pure-tone amplitudes by multiplying the transient-state-pure-tone amplitudes with the predicted pure-tone amplitudes; andextracting the natural frequency of the spring which corresponds to a local maximum value among the filtered pure-tone amplitudes.2. The method according to claim 1 , wherein said expected steady-state amplitude is calculated based on the amplitudes at least two time points within a duration of the input sound.4. The method according to claim 2 , wherein a difference between the two different time points is a period of the natural frequency of the corresponding spring.5. The method according ...

VOLUME LEVELER CONTROLLER AND CONTROLLING METHOD

Volume leveler controller and controlling method are disclosed. In one embodiment, A volume leveler controller includes an audio content classifier for identifying the content type of an audio signal in real time; and an adjusting unit for adjusting a volume leveler in a continuous manner based on the content type as identified. The adjusting unit may configured to positively correlate the dynamic gain of the volume leveler with informative content types of the audio signal, and negatively correlate the dynamic gain of the volume leveler with interfering content types of the audio signal. 1. A loudness normalization method based upon target loudness , the method comprising:determining one or more dynamic gain parameters based upon a content type or context; andmodifying a loudness of an audio signal by employing the selected gain parameters, wherein a resulting loudness level of an audio recording on playback is consistent over a timeline based on a target loudness value.2. The loudness normalization method of claim 1 , wherein the dynamic gain parameters are identified and applied in real time.3. The loudness normalization method of claim 1 , wherein the content type comprises speech claim 1 , short-term music claim 1 , noise and/or background sound.4. The loudness normalization method of claim 1 , wherein dialog enhancement is applied having an effect of making dialog more prominent within a particular context.5. The loudness normalization method of claim 1 , wherein a loudness equalization is applied to have an effect on one or more playback levels on a tonal balance.6. The loudness normalization method of claim 1 , wherein a parameter smoothing is applied to the dynamic gain parameters.7. An apparatus configured to normalize loudness based upon target loudness claim 1 , comprising:at least one processor; and in which the at least one memory with the computer program is configured with the at least one processor to cause the audio processing apparatus to at least ...

POST-PROCESSING GAINS FOR SIGNAL ENHANCEMENT

A method, an apparatus, and logic to post-process raw gains determined by input processing to generate post-processed gains, comprising using one or both of delta gain smoothing and decision-directed gain smoothing. The delta gain smoothing comprises applying a smoothing filter to the raw gain with a smoothing factor that depends on the gain delta: the absolute value of the difference between the raw gain for the current frame and the post-processed gain for a previous frame. The decision-directed gain smoothing comprises converting the raw gain to a signal-to-noise ratio, applying a smoothing filter with a smoothing factor to the signal-to-noise ratio to calculate a smoothed signal-to-noise ratio, and converting the smoothed signal-to-noise ratio to determine the second smoothed gain, with smoothing factor possibly dependent on the gain delta. 1. An audio processing apparatus , comprising:at least one processor; andat least one memory storing a computer program; receive at least one input audio signal,', 'determine raw gains to carry out dynamic range control (DRC), and', 'modify the DRC gains and apply them to the input audio signal to remove audible artifacts from the audio output signal., 'in which the at least one memory with the computer program is configured with the at least one processor to cause the audio processing apparatus to at least2. The apparatus of claim 1 , wherein the gains are applied to carry-out dynamic equalization3. The apparatus of claim 1 , wherein post-processing is applied to the DRC gains to carry out gain smoothing of the modified DRC gains.4. The apparatus of claim 3 , wherein a first order linear smoothing filter is employed as post processor.5. The apparatus of claim 3 , wherein a delta smoothing post processor is employed.6. The apparatus of claim 5 , wherein the smoothing is controlled according to the output of a voice activity detector (VAD).7. The apparatus of claim 3 , wherein the post-processing is applied when there is a ...

NOISE SUPPRESSOR AND METHOD OF IMPROVING AUDIO INTELLIGIBILITY

There is provided a noise suppressor comprising a receiver operable to receive an input audio signal and to produce from the input audio signal a first signal and a second signal the input audio signal comprising desired audio and transmission end noise. The noise suppressor further comprises a first processor operable to perform a first process on the first signal the first process comprising noise suppression to remove at least a portion of the transmission end noise from the first signal before outputting the first signal to a first audio channel The noise suppressor further comprises a second processor operable to perform a second process on the second signal the second process comprising outputting the second signal 18 to a second audio channel The first process comprises more aggressive noise suppression than the second process. 1. A noise suppressor comprising:a receiver operable to receive an input audio signal and to produce from the input audio signal a first signal and a second signal, the input audio signal comprising desired audio and transmission end noise;a first processor operable to perform a first process on the first signal, the first process comprising noise suppression to remove at least a portion of the transmission end noise from the first signal before outputting the first signal to a first audio channel; anda second processor operable to perform a second process on the second signal, the second process comprising outputting the second signal to a second audio channel.2. The noise suppressor of claim 1 , whereinthe second process comprises noise suppression, andthe noise suppression of the first process is more aggressive than the noise suppression of the second process.3. The noise suppressor of claim 1 , wherein the second process does not comprise noise suppression.4. The noise suppressor of claim 1 , wherein the first process further comprises introducing a time delay to the first signal before outputting the first signal to the first ...

Enhanced De-Esser For In-Car Communication Systems

Methods and systems for deessing of speech signals are described. A deesser of a speech processing system includes an analyzer configured to receive a full spectral envelope for each time frame of a speech signal presented to the speech processing system, and to analyze the full spectral envelope to identify frequency content for deessing. The deesser also includes a compressor configured to receive results from the analyzer and to spectrally weight the speech signal as a function of results of the analyzer. The analyzer can be configured to calculate a psychoacoustic measure from the full spectral envelope, and may be further configured to detect sibilant sounds of the speech signal using the psychoacoustic measure. The psychoacoustic measure can include, for example, a measure of sharpness, and the analyzer may be further configured to calculate deesser weights based on the measure of sharpness. An example application includes in-car communications. 1. A method of deessing a speech signal , the method comprising:a) for each time frame of a speech signal presented to a speech processing system, analyzing a full spectral envelope to identify frequency content for deessing; andb) spectrally weighting the speech signal as a function of results of the analyzing.2. The method of claim 1 , wherein the analyzing includes calculating a psychoacoustic measure from the full spectral envelope.3. The method of claim 2 , wherein the analyzing further includes detecting sibilant sounds of the speech signal using the psychoacoustic measure.4. The method of claim 2 , wherein the psychoacoustic measure includes at least one of a measure of sharpness and a measure of roughness.5. The method of claim 2 , wherein the psychoacoustic measure includes a measure of sharpness claim 2 , and wherein the analyzing further includes calculating deesser weights based on the measure of sharpness.6. The method of claim 1 , wherein the spectrally weighting the speech signal includes applying ...

METHOD AND SYSTEM FOR NORMALIZING PLATFORM-ADAPTIVE AUDIO

A method for normalizing platform-adaptive audio includes encoding input video content and generating video stream data as original data to store the video stream data in storage; generating loudness metadata for audio data of the video content and storing the loudness metadata in the storage; receiving a request for the video content from a client; searching the storage for video stream data of the video content corresponding to the request, the loudness metadata, and a device profile corresponding to device information included in the request; and transmitting, to the client, a response including the video stream data, the loudness metadata, and the device profile that are found in the storage. 1. A platform adaptive audio normalization method performed by a computer device having at least one processor , the platform adaptive audio normalization method comprising:encoding input video content, generating video stream data as original data, and storing the video stream data in a storage;generating loudness metadata for audio data of the video content and storing the loudness metadata in the storage;receiving a request for the video content from a client;retrieving the video stream data of the video content corresponding to the request, the loudness metadata, and a device profile corresponding to device information included in the request from the storage; andtransmitting a response that includes the video stream data, the loudness metadata, and the device profile retrieved from the storage to the client.2. The platform adaptive audio normalization method of claim 1 , wherein the device profile includes an adjustment value that adjusts a normalization factor by analyzing at least one of a number claim 1 , positions claim 1 , and distances of audio output devices of a playback device based on audio that is output through the playback device for playing back the video content and is input at a preset playback position.3. The platform adaptive audio normalization ...

Effective Pre-Echo Attenuation in a Digital Audio Signal

A method is provided for processing pre-echo attenuation in a digital audio signal generated from a transform coding, wherein, at the decoding point, the method includes: detection of a position of attack in the decoded signal; determination of a pre-echo region preceding the position of attack detected in the decoded signal; calculation of attenuation factors per sub-block of the pre-echo region, according to at least the frame wherein the attack has been detected and the preceding frame; and pre-echo attenuation in the sub-blocks of the pre-echo region by the corresponding damping factors. The method also includes application of a filter for the spectral shaping of the pre-echo region on the current frame up to the detected position of the attack. A device and a decoder including the device are also proved for implementing the method. 1. A method of processing attenuation of pre-echo in a digital audio signal engendered on the basis of a transform-based coding , in which , on decoding , the method comprises the following performed by a processing device:detection of an attack position in the decoded signal;determination of a pre-echo zone preceding the attack position detected in the decoded signal;calculation of attenuation factors per sub-block of the pre-echo zone, as a function at least of the frame in which the attack has been detected and of the previous frame;attenuation of pre-echo in the sub-blocks of the pre-echo zone by the corresponding attenuation factors; andapplication of an adaptive filtering of spectral shaping of the pre-echo zone on the current frame until as far as the detected position of the attack.2. The method as claimed in claim 1 , wherein the method furthermore comprises calculation of at least one decision parameter regarding the filtering to be applied to the pre-echo zone and the adaptation of the coefficients of the filtering as a function of said at least one decision parameter.3. The method as claimed in claim 2 , wherein at least ...

METHODS AND SYSTEM FOR CONTROLLING TACTILE CONTENT

An audio system presented herein includes a transducer array, sensor array, and a controller. The controller control tactile content imparted to a user via actuation of at least one transducer in the transducer array while presenting audio content to the user. The transducer array presents the audio content with the tactile content to the user. The audio system can be part of a headset. 1. An audio system comprising:at least one transducer configured to present acoustic content and tactile content to a user; anda controller configured to control the tactile content imparted to the user via actuation of the at least one transducer by altering spectral content of the acoustic content to improve perception of the tactile content, whereinthe at least one transducer is further configured to present the acoustic content having the altered spectral content and the tactile content to the user.2. The audio system of claim 1 , wherein the controller is further configured to provide navigation instructions to the user using the tactile content.3. The audio system of claim 2 , wherein:the at least one transducer comprises at least one cartilage conduction transducer attached to a corresponding ear of the user; andthe controller is further configured to selectively apply the tactile content to the corresponding ear via the at least one cartilage conduction transducer to provide the navigation instructions to the user.4. The audio system of claim 1 , wherein the controller is further configured to increase speech intelligibility for audio content presented to the user by controlling the tactile content claim 1 , the audio content comprising the acoustic content and the tactile content.5. The audio system of claim 1 , wherein the controller is further configured to generate audio content having a defined level of a near field effect by controlling the tactile content claim 1 , the audio content comprising the acoustic content and the tactile content.6. The audio system of claim 1 ...

MODIFICATION OF AUDIO SIGNAL BASED ON USER AND LOCATION

In one aspect, a device includes a processor and storage accessible to the processor. The storage bears instructions executable by the processor to receive at least one audio signal, identify one or more of a user associated with at least one received audio signal and a location of the user, and modify at least one received audio signal based at least in part on identification of one or more of the user and the location. 1. A device , comprising:a processor; andstorage accessible to the processor and bearing instructions executable by the processor to:receive at least one audio signal;identify one or more of a user associated with at least one received audio signal and a location of the user; andbased at least in part on identification of one or more of the user and the location, modify at least one received audio signal by adjusting an accent of words spoken by the user from a first accent associated with a first geographic region to a second accent associated with a second geographic region different from the first geographic region.2. The device of claim 1 , wherein the device is a first device claim 1 , and wherein the instructions are executable by the processor to:transmit the modified audio signal to a second device different from the first device.3. The device of claim 1 , comprising at least one speaker claim 1 , wherein the instructions are executable by the processor to:present, using the speaker, audio output based on the audio signal.4. The device of claim 1 , wherein at least one received audio signal is modified using digital signal processing.5. The device of claim 1 , comprising a microphone claim 1 , wherein the at least one audio signal is received from the microphone.6. The device of claim 1 , wherein the device is a first device claim 1 , and wherein the at least one audio signal is received from a second device different from the first device.7. (canceled)8. The device of claim 1 , wherein the instructions are executable by the processor to: ...

Sound Field Related Rendering

An apparatus for spatial audio reproduction including circuitry configured to: obtain at least one focus parameter configured to define a focus shape; process a spatial audio signal that represents an audio scene to generate a processed spatial audio signal that represents a modified audio scene, so as to control relative emphasis in, at least in part, a portion of the spatial audio signal in the focus shape relative to at least in part; other portions of the spatial audio signals outside the focus shape and output the processed spatial audio signal, wherein the modified audio scene enables the relative emphasis in, at least in part, the portion of the spatial audio signal in the focus shape relative to at least in part other portions of the spatial audio signals outside the focus shape. 1. An apparatus comprising at least one processor and at least one non-transitory memory including a computer program code , the at least one memory and the computer program code configured to , with the at least one processor , cause the apparatus at least to:obtain at least one focus parameter configured to define a focus shape;process a spatial audio signal that represents an audio scene to generate a processed spatial audio signal that represents a modified audio scene, so as to control relative emphasis in, at least in part, a portion of the spatial audio signal in the focus shape relative to at least in part other portions of the spatial audio signals outside the focus shape; andoutput the processed spatial audio signal, wherein the modified audio scene enables the relative emphasis in, at least in part, the portion of the spatial audio signal in the focus shape relative to at least in part other portions of the spatial audio signals outside the focus shape.2. The apparatus according to claim 1 , wherein at least one focus parameter is further configured to define a focus amount claim 1 , and the at least one memory and the computer program code are configured to claim 1 , ...

Training a voice morphing apparatus

Systems and methods for training a voice morphing apparatus are described. The voice morphing apparatus is trained to morph input audio data to mask an identity of a speaker. Training is performed by evaluating an objective function that is a function of the input audio data and an output of the voice morphing apparatus. The objective function may have a first term that is based on speaker identification and a second term that is based on audio fidelity. By optimizing the objective function, parameters of the voice morphing apparatus may be adjusted so as to reduce a confidence of speaker identification and maintain an audio fidelity of the morphed audio data. The voice morphing apparatus, once trained, may be used as part of an automatic speech recognition system.

ENHANCING AUDIO USING MULTIPLE RECORDING DEVICES

In general, the subject matter described in this disclosure can be embodied in methods, systems, and program products for identifying that a first audio stream includes first, second, and third sources of audio. A computing system identifies that a second audio stream includes the first, second, and third sources of audio. The computing system determines that the first and second sources of audio are part of a first conversation. The computing system generates a third audio stream that combines the first source of audio from the first audio stream, the first source of audio from the second audio stream, the second source of audio from the first audio stream, and the second source of audio from the second audio stream, and diminishes the third source of audio from the first audio stream, and the third source of audio from the second audio stream. 1. A computer-implemented method for enhancing audio , the method comprising:receiving, using a hardware processor, an audio stream for playback on a media device;extracting, using the hardware processor, a first audio source, a second audio source, and a third audio source from the audio stream;determining, using the hardware processor, that a conversation between the first audio source and the second audio source occurs within a first portion of the audio stream and a second conversation between the first audio source and the third audio source occurs within a second portion of the audio stream at a second time point; andgenerating, using the hardware processor, an updated audio stream that enhances the first audio source and the second audio source extracted from the first portion of the audio stream and diminishes the third audio source extracted from the first portion of the audio stream and that enhances the first audio source and the third audio source extracted from the second portion of the audio stream and diminishes the second audio source extracted from the second portion of the audio stream.2. The computer- ...

System and method for artifact masking

A system for processing audio data comprising a first signal processing path configured to generate a mask control signal. A second signal processing path configured to generate a decorrelated input audio signal. A mixer configured to mix the mask control signal and the decorrelated input audio signal and to generate an output.

VOICE SIGNAL PROCESSING APPARATUS AND VOICE SIGNAL PROCESSING METHOD

A voice signal processing apparatus and a voice signal processing method are provided. A loudness of an input voice signal is detected to obtain a reference loudness. Reference loudness gains corresponding to frequency bands are calculated according to the reference loudness and wide dynamic range compression curves corresponding to the frequency bands. Loudnesses of filter signals of the frequency bands are adjusted according to the reference loudness gains of the frequency bands. 1. A voice signal processing apparatus , comprising:an input voice signal filter receiving an input voice signal and filtering the input voice signal to generate a plurality of filter signals of different frequency bands; anda processor detecting a loudness of the input voice signal to obtain a reference loudness, calculating reference loudness gains corresponding to the frequency bands according to the reference loudness and wide dynamic range compression curves corresponding to the frequency bands, multiplying the filter signals by the reference loudness gains corresponding to the filter signals to obtain a plurality of loudness adjusted filter signals corresponding to the frequency bands, and adding up the loudness adjusted filter signals to generate an output voice signal.2. The voice signal processing apparatus according to claim 1 , wherein the wide dynamic range compression curves are obtained by performing wide dynamic range compression processes corresponding to the frequency bands on a unit gain curve claim 1 , and the processor further calculates the reference loudness gains according to first output loudnesses corresponding to the reference loudness on the wide dynamic range compression curves corresponding to the frequency bands and a second output loudness corresponding to the reference loudness on the unit gain curve.3. The voice signal processing apparatus according to claim 1 , wherein the processor further detects loudnesses of the filter signals to obtain a plurality of ...

Audio Signal Processing Method and Apparatus and Differential Beamforming Method and Apparatus

An audio signal processing method and apparatus and a differential beamforming method and apparatus to resolve a problem that an existing audio signal processing system cannot process audio signals in multiple application scenarios at the same time. The method includes determining a super-directional differential beamforming weighting coefficient, acquiring an audio input signal and determining a current application scenario and an audio output signal, acquiring, a weighting coefficient corresponding to the current application scenario, performing super-directional differential beamforming processing on the audio input signal using the acquired weighting coefficient in order to obtain a super-directional differential beamforming signal in the current application scenario, and performing processing on the formed signal to obtain a final audio signal required by the current application scenario. By using this method, a requirement that different application scenarios require different audio signal processing manners can be met.

Audio Device with Speech-Based Audio Signal Processing

An audio device with an electro-acoustic transducer and a processor that is configured to determine if input audio signals are speech-based, and if the input audio signals are determined to be speech-based apply speech dynamic range compression to the input audio signals, to develop revised audio signals. The revised audio signals are provided to the transducer. 1. A computer program product having a non-transitory computer-readable medium including computer program logic encoded thereon that , when performed on an audio device that is configured to play audio signals over an electro-acoustic transducer , causes the audio device to:determine if input audio signals are speech-based;if the input audio signals are determined to be speech-based, apply speech dynamic range compression to the input audio signals, to develop revised audio signals; andprovide the revised audio signals to the transducer.2. The computer program product of claim 1 , wherein if the input audio signals are determined to be speech-based the computer program product further causes the audio device to apply at least one of speech static equalization or speech dynamic equalization to the input audio signals.3. The computer program product of claim 2 , wherein if the input audio signals are not determined to be speech-based the computer program product causes the audio device to apply at least one of non-speech static equalization claim 2 , non-speech dynamic equalization claim 2 , or non-speech dynamic range compression to the input audio signals.4. The computer program product of claim 3 , wherein if the input audio signals are not determined to be speech-based the computer program product causes the audio device to apply non-speech static equalization claim 3 , non-speech dynamic equalization claim 3 , and non-speech dynamic range compression to the input audio signals.5. The computer program product of claim 3 , wherein speech static equalization has less low frequency compensation and more high ...

SPEECH SIGNAL PROCESSING METHOD AND APPARATUS

A speech signal processing method is performed at a terminal device, including: obtaining a recorded signal and a to-be-output speech signal, the recorded signal including a noise signal and an echo signal; calculating a loop transfer function according to the recorded signal and the speech signal; calculating a power spectrum of the echo signal and a power spectrum of the noise signal according to the recorded signal, the speech signal, and the loop transfer function; calculating a frequency weighted coefficient according to the two power spectra of the echo signal and the noise signal; adjusting a frequency amplitude of the speech signal based on the frequency weighted coefficient; and outputting the adjusted speech signal to a speaker electrically coupled to the terminal device. As such, the frequency amplitude of the speech signal is automatically adjusted according to the relative frequency distribution of a noise signal and the speech signal. 1. A speech signal processing method performed at a terminal device having one or more processors , a microphone , a speaker , and memory storing one or more programs to be executed by the one or more processors , the method comprising:receiving, via an instant messaging application, a speech signal from a second terminal device, wherein the second terminal device is connected to the terminal device via a computer network;recording, via the microphone, an audio signal, the audio signal including a noise signal from an environment surrounding the terminal device and an echo signal from the speaker;calculating a loop transfer function using the recorded audio signal and the speech signal;calculating a power spectrum of the echo signal and a power spectrum of the noise signal using the recorded audio signal, the speech signal and the loop transfer function;calculating a frequency weighted coefficient according to the power spectrum of the echo signal and the power spectrum of the noise signal, wherein the frequency weighted ...

Enhancing An Audio Recording

A system and method are provided for enhancing an audio recording which comprises a recording of a sound signal obtained from the play-out of an audio signal via a speaker. The audio signal, and thereby the sound signal, may represent certain audio content, e.g., a radio station or TV audio. To perform the enhancing, the recording of the sound signal is suppressed using the audio signal, thereby obtaining an intermediate audio recording. An original version of the audio content is then added to the intermediate audio recording to obtain an enhanced audio recording. This original version is generally of higher quality as it generally does not represent a background audio component but rather was purposefully recorded or generated.

Automated equalization

Techniques for improving speech recognition are described. An example of an electronic device includes an extracting unit to extract a reference spectral profile from a reference signal and a device spectral profile from a device signal. A comparing unit compares the reference spectral profile and the device spectral profile. A delta calculating unit calculates a delta between the reference spectral profile and the device spectral profile. A design unit designs a correction filter based on the computed delta. 1. An electronic device for improving speech recognition of a device under test (DUT) , comprising:an extracting unit to extract a reference spectral profile from a reference signal and a DUT spectral profile from a DUT signal;a comparing unit to compare the reference spectral profile and the DUT spectral profile;a delta calculating unit to compute a delta between the reference spectral profile and the DUT spectral profile to obtain a computed delta; anda design unit to design a correction filter based on the computed delta.2. The electronic device of claim 1 , comprising a first calculating unit to calculate the reference signal from a set of recordings.3. The electronic device of claim 1 , wherein the design unit designs the correction filter using a plurality of recordings claim 1 , and wherein the plurality of recordings are obtained from one or more devices.4. The electronic device of claim 1 , comprising an application unit to apply the correction filter to a microphone of the DUT.5. The electronic device of claim 4 , comprising an orientation sensor to determine an orientation of the DUT and employ an appropriate correction filter.6. The electronic device of claim 4 , comprising a proximity sensor to determine a distance from a user to the DUT and employ the appropriate correction filter.7. The electronic device of claim 4 , comprising an angle sensor to determine an angle between the user and the DUT and employ the appropriate correction filter.8. The ...

Apparatus and Method for Power Efficient Signal Conditioning for a Voice Recognition System

A disclosed method includes monitoring an audio signal energy level while having a plurality of signal processing components deactivated and activating at least one signal processing component in response to a detected change in the audio signal energy level. The method may include activating and running a voice activity detector on the audio signal in response to the detected change where the voice activity detector is the at least one signal processing component. The method may further include activating and running the noise suppressor only if a noise estimator determines that noise suppression is required. The method may activate and runs a noise type classifier to determine the noise type based on information received from the noise estimator and may select a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient.