公开(公告)号：EP3373132A3

公开(公告)日：2018-11-21

申请号：EP18153840.6

申请日：2018-01-29

Applicant: LG Electronics Inc.

Inventor： CHO, Sungil ,  KIM, Youngjun ,  JANG, Yujune

IPC: G06F3/16 ,  G10L15/22

CPC classification number: H04R3/12 ,  G06F3/16 ,  G06F3/167 ,  G10L15/07 ,  G10L2021/02165 ,  H04R2430/01 ,  H04R2499/13 ,  H04W4/046 ,  H04W4/44

Abstract: A terminal using machine learning for selecting an output mode based on the context information of a user. An embodiment of a terminal may include an audio output unit, a display, and a controller configured to obtain context information of a user, set an output mode of the mobile terminal based on the obtained context information, convert communication information of a first type received from an external device to a second type associated with the set output mode when the first type and the second type are different, and control the audio output unit or the display to output the communication information, wherein the audio output unit or the display is used to output the communication information based on the output mode. An embodiment may include a data learning unit configured to store data to implement machine learning and logic based determinations for selecting the output mode.

公开(公告)号：EP3392668A1

公开(公告)日：2018-10-24

申请号：EP18174931.8

申请日：2009-04-24

Applicant: Nokia Technologies Oy

Inventor： NIEMISTO, Riitta Elina ,  VALVE, Paivi Marianna

IPC: G01S3/808 ,  G10L25/78 ,  G10L21/0216

CPC classification number: G10L25/78 ,  G10L2021/02165 ,  G10L2021/02166

Abstract: In accordance with an example embodiment of the invention, there is provided an apparatus for detecting voice activity in an audio signal. The apparatus comprises a first voice activity detector (6b) for making a first voice activity detection decision (D2) based at least in part on the voice activity of a first audio signal (A1) received from a first microphone (1a). The apparatus also comprises a second voice activity detector (6a) for making a second voice activity detection decision (D1) based at least in part on an estimate of a direction of the first audio signal (A1) and an estimate of a direction of a second audio signal (A2) received from a second microphone (1b). The apparatus further comprises a classifier (6c) for making a third voice activity detection decision (D3) based at least in part on the first and second voice activity detection decisions.

公开(公告)号：EP2966643B1

公开(公告)日：2018-07-25

申请号：EP15177849.5

申请日：2013-04-15

Applicant: Cirrus Logic, Inc.

Inventor： Alderson, Jeffrey ,  Hendrix, Jon D. ,  Zhou, Dayong ,  Miller, Antonio John ,  Yong, Chin ,  Kamath, Gautham Devendra

IPC: G10K11/178

CPC classification number: G10K11/178 ,  G10K11/16 ,  G10K2210/00 ,  G10K2210/108 ,  G10K2210/3014 ,  G10K2210/3017 ,  G10K2210/3028 ,  G10K2210/30391 ,  G10L2021/02165 ,  H04B3/237

Abstract: A personal audio device includes a personal audio device housing; a transducer mounted on the housing for reproducing an audio signal including an anti-noise signal (anti-noise) for countering effects of ambient audio sounds in an acoustic output of the output transducer; a reference microphone mounted on the housing for providing a reference microphone signal (ref) indicative of the ambient audio sounds; and a processing circuit (30) within the housing. The processing circuit (30) adaptively generates the anti-noise signal (anti-noise) from the reference microphone signal (ref) such that the anti-noise signal (anti-noise) causes substantial cancellation of the ambient audio sounds. The processing circuit (30), in response to determining that an amplitude of acoustic leakage of the source audio into the reference microphone is substantial with respect to an amplitude of the ambient audio sounds, takes action to prevent improper generation of the anti-noise signal (anti-noise).

公开(公告)号：EP2974367B1

公开(公告)日：2018-07-04

申请号：EP14705002.5

申请日：2014-02-03

Applicant: Google Technology Holdings LLC

Inventor： BASTYR, Kevin J. ,  DAVIS, Giles T. ,  IVANOV, Plamen A. ,  OLIVEIRA, Rivanaldo S. ,  RAMABADRAN, Tenkasi V. ,  SINGARAJU, Snehitha

IPC: H04R3/00 ,  G10L21/0208 ,  G10L15/01 ,  G10L25/78 ,  G10L21/0216

CPC classification number: G10L21/0208 ,  G10L15/01 ,  G10L15/20 ,  G10L25/78 ,  G10L2021/02165 ,  G10L2021/02166 ,  H04R3/005

Abstract: One method of operation includes beamforming a plurality of microphone outputs to obtain a plurality of virtual microphone audio channels. Each virtual microphone audio channel corresponds to a beamform. The virtual microphone audio channels include at least one voice channel and at least one noise channel. The method includes performing voice activity detection on the at least one voice channel and adjusting a corresponding voice beamform until voice activity detection indicates that voice is present on the at least one voice channel. Another method beamforms the plurality of microphone outputs to obtain a plurality of virtual microphone audio channels, where each virtual microphone audio channel corresponds to a beamform, and with at least one voice channel and at least one noise channel. The method performs voice recognition on the at least one voice channel and adjusts the corresponding voice beamform to improve a voice recognition confidence metric.

公开(公告)号：EP3314908A1

公开(公告)日：2018-05-02

申请号：EP16814976.3

申请日：2016-05-26

Applicant: Intel IP Corporation

Inventor： KAR, Swarnendu ,  CHATLANI, Navin

IPC: H04R3/00

CPC classification number: G10L21/0232 ,  G10L25/78 ,  G10L2021/02165 ,  H04R3/005

Abstract: In one example a controller comprises logic, at least partially including hardware logic, configured to detect speech activity in an audio signal received in a non-aerial microphone and in response to the voice activity, to apply a noise cancellation algorithm to a speech input received in a aerial microphone. Other examples may be described.

公开(公告)号：EP2760021B1

公开(公告)日：2018-01-17

申请号：EP13153065.1

申请日：2013-01-29

Applicant: 2236008 Ontario Inc.

Inventor： Paranjpe, Shreyas ,  Hetherington, Phillip Alan

IPC: G10L21/0208

CPC classification number: G10L21/0208 ,  G10L2021/02082 ,  G10L2021/02165

Abstract: In a system and method for maintaining the spatial stability of a sound field a balance gain may be calculated for two or more microphone signals. The balance gain may be associated with a spatial image in the sound field. Signal values may be calculated for each of the microphone. The signal values may be signal estimates or signal gains calculated to improve a characteristic of the microphone signals. The differences between the signal values associated with each microphone signal may be limited although some difference between signal values may be allowable. One or more microphone signals are adjusted responsive to the two or more balance gains and the signal gains to maintain the spatial stability of the sound field. The adjustments of one or more microphone signals may include mixing of two or more microphone. The signal gains are applied to the two or more microphone signals.

公开(公告)号：EP3113183A4

公开(公告)日：2017-07-26

申请号：EP15755932

申请日：2015-02-12

Applicant: NAT INST INF & COMM TECH

Inventor： SHIGA YOSHINORI

IPC: G10L21/0232 ,  G10L21/0216 ,  G10L21/0364 ,  G10L25/15 ,  H04R27/00

CPC classification number: G10L21/0332 ,  G10L13/033 ,  G10L19/0204 ,  G10L21/007 ,  G10L21/0208 ,  G10L21/0232 ,  G10L21/0364 ,  G10L25/15 ,  G10L2021/02165 ,  H04R27/00 ,  H04R2227/009

Abstract: [Object] To provide a speech intelligibility improving apparatus capable of generating highly intelligible speech in various environments without unnecessarily amplifying sound volume. [Solution] A speech intelligibility improving apparatus 250 includes: an envelope surface extracting unit 292 extracting, from a spectrum of speech signal 254 as an object of processing, a curve representing a general outline of peaks of spectral envelope in contact with or along local peaks of spectral envelope of the spectrum; a noise adapting unit 300 modifying spectrum of speech signal 254 based on the curve extracted by envelope surface extracting unit 292; and a sinusoidal wave speech synthesizing unit 305 generating a modified speech signal 260 for the speech improved in intelligibility based on the spectrum modified by noise adapting unit 300.

Abstract translation: 本发明的目的在于提供一种能够在各种环境下生成高度清晰的语音而不会不必要地放大音量的语音清晰度改善装置。 解决方案语音清晰度改善装置250包括：包络表面提取单元292，从作为处理对象的语音信号254的频谱中提取表示与局部峰值接触或沿着局部峰值的频谱包络的​​峰值的总体轮廓的曲线 谱的谱包络; 噪声适应单元300，其基于由包络面提取单元292提取的曲线来修改语音信号254的频谱; 以及正弦波语音合成单元305，其基于由噪声适应单元300修改的频谱来生成用于可理解性提高的语音的修改语音信号260。

公开(公告)号：EP3147901A1

公开(公告)日：2017-03-29

申请号：EP16185469.0

申请日：2016-08-24

Applicant: FUJITSU LIMITED

Inventor： Matsuo, Naoshi

IPC: G10L21/0216

CPC classification number: G10L25/93 ,  G10L15/02 ,  G10L15/20 ,  G10L21/0216 ,  G10L25/78 ,  G10L25/87 ,  G10L2021/02165 ,  G10L2021/02168

Abstract: An audio signal processing device that includes: a processor configured to execute a procedure, the procedure comprising: detecting a speech segment of an audio signal; suppressing noise in the audio signal; and adjusting an amount of suppression of noise such that the amount of suppression during a specific period, which starts from a position based on a terminal end of the detected speech segment and is a period shorter than a period spanning from the terminal end of the detected speech segment to a starting end of a next speech segment, becomes greater than in other segments, and a memory configured to store audio signals before and after noise suppression and the amount of suppression before and after adjustment.

Abstract translation: 一种音频信号处理装置，并包括：被配置为执行一个过程，该过程包括处理器：检测音频信号的语音段; 抑制所述音频信号的噪声; 和调整达噪声的抑制检查确实抑制在特定期间的量，这从基于检测到的语音段的末端的位置开始，并且周期比一个周期从所检测的终端跨越短 语音段到下一个语音段的起始端，变得比在其它段时，和存储器，被配置之前和噪声抑制和抑制的前和调整后的量之后存储的音频信号。

公开(公告)号：EP2594059A4

公开(公告)日：2017-02-22

申请号：EP11807605

申请日：2011-07-15

Applicant: ALIPH INC

Inventor： BURNETT GREGORY C ,  GOERTZ MICHAEL ,  PETIT NICOLAS ,  JING ZHINIAN ,  FORESTIERI STEVE ,  DONALDSON THOMAS

IPC: H04M3/42 ,  G10L21/0208 ,  G10L21/0216 ,  H04M1/725 ,  H04M3/56 ,  H04R1/10 ,  H04R1/40 ,  H04R3/00 ,  H04R3/04 ,  H04W4/16 ,  H04W88/16

CPC classification number: H04M3/56 ,  G10L21/0208 ,  G10L2021/02082 ,  G10L2021/02165 ,  H04M1/7253 ,  H04M3/568 ,  H04M2203/509 ,  H04M2250/62 ,  H04R1/1083 ,  H04R1/406 ,  H04R3/005 ,  H04R3/04 ,  H04R2420/07 ,  H04W4/16 ,  H04W88/16

公开(公告)号：EP3120355A2

公开(公告)日：2017-01-25

申请号：EP15707356.0

申请日：2015-03-02

Applicant: Koninklijke Philips N.V.

Inventor： JANSE, Cornelis Pieter ,  VAN STUIVENBERG, Leonardus Cornelis Antonius ,  KECHICHIAN, Patrick

IPC: G10L21/0208 ,  G10L25/18

CPC classification number: G10L21/0232 ,  G10L21/0208 ,  G10L21/04 ,  G10L25/18 ,  G10L2021/02087 ,  G10L2021/02165 ,  G10L2021/02166 ,  H04R3/005

Abstract: A noise suppressor comprises a first (401) and a second transformer (403) for generating a first and second frequency domain signal from a frequency transform of a first and second microphone signal. A gain unit (405, 407, 409) determines time frequency tile gains in response to a difference measure for magnitude time frequency tile values of the first frequency domain signal and magnitude time frequency tile values of the second frequency domain signal. A scaler (411) generates a third frequency domain signal by scaling time frequency tile values of the first frequency domain signal by the time frequency tile gains; and the resulting signal is converted to the time domain by a third transformer (413). A designator (405, 407, 415) designates time frequency tiles of the first frequency domain signal as speech tiles or noise tiles; and the gain unit (409) determines the gains in response to the designation of the time frequency tiles as speech tiles or noise tiles.

Abstract translation: 噪声抑制器包括用于从第一和第二麦克风信号的频率变换产生第一和第二频域信号的第一（401）和第二变换器（403）。 增益单元（405,407,409）响应于所述第一频域信号的幅度时间频率瓦片值和所述第二频域信号的幅度时间频率瓦片值的差测量来确定时间频率瓦片增益。 缩放器（411）通过按照时间频率瓦片增益缩放第一频域信号的时间频率瓦片值来产生第三频域信号; 并且由第三变压器（413）将所得到的信号转换成时域。 指示符（405,407,415）指定第一频域信号的时间频率瓦片作为语音瓦片或噪声瓦片; 并且增益单元（409）响应于将时间频率瓦片指定为语音瓦片或噪声瓦片来确定增益。