Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020108614 - AUDIO RECOGNITION METHOD, AND TARGET AUDIO POSITIONING METHOD, APPARATUS AND DEVICE

Publication Number WO/2020/108614
Publication Date 04.06.2020
International Application No. PCT/CN2019/121946
International Filing Date 29.11.2019
IPC
G01S 5/20 2006.01
GPHYSICS
01MEASURING; TESTING
SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
5Position-fixing by co-ordinating two or more direction or position-line determinations; Position-fixing by co-ordinating two or more distance determinations
18using ultrasonic, sonic, or infrasonic waves
20Position of source determined by a plurality of spaced direction-finders
G10L 15/20 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
20Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise or of stress induced speech
CPC
G01S 3/802
GPHYSICS
01MEASURING; TESTING
SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
3Direction-finders for determining the direction from which infrasonic, sonic, ultrasonic, or electromagnetic waves, or particle emission, not having a directional significance, are being received
80using ultrasonic, sonic or infrasonic waves
802Systems for determining direction or deviation from predetermined direction
G10L 2021/02082
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
02Speech enhancement, e.g. noise reduction or echo cancellation
0208Noise filtering
02082the noise being echo, reverberation of the speech
G10L 2021/02166
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
02Speech enhancement, e.g. noise reduction or echo cancellation
0208Noise filtering
0216characterised by the method used for estimating noise
02161Number of inputs available containing the signal or the noise to be suppressed
02166Microphone arrays; Beamforming
G10L 21/0208
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
02Speech enhancement, e.g. noise reduction or echo cancellation
0208Noise filtering
G10L 21/0216
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
02Speech enhancement, e.g. noise reduction or echo cancellation
0208Noise filtering
0216characterised by the method used for estimating noise
G10L 21/0224
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
02Speech enhancement, e.g. noise reduction or echo cancellation
0208Noise filtering
0216characterised by the method used for estimating noise
0224Processing in the time domain
Applicants
  • 腾讯科技(深圳)有限公司 TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED [CN]/[CN]
Inventors
  • 郑脊萌 ZHENG, Jimeng
  • 刘二男 LIU, Ian Ernan
  • 高毅 GAO, Yi
  • 黎韦伟 LI, Weiwei
Agents
  • 北京德琦知识产权代理有限公司 DEQI INTELLECTUAL PROPERTY LAW CORPORATION
Priority Data
201811455880.630.11.2018CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) AUDIO RECOGNITION METHOD, AND TARGET AUDIO POSITIONING METHOD, APPARATUS AND DEVICE
(FR) PROCÉDÉ DE RECONNAISSANCE AUDIO ET PROCÉDÉ, APPAREIL ET DISPOSITIF DE POSITIONNEMENT AUDIO CIBLE
(ZH) 音频识别方法、定位目标音频的方法、装置和设备
Abstract
(EN)
Disclosed are a sound source azimuth angle operational method, a method and apparatus for an audio interactive device to position target audio, and an audio interactive device. The sound source azimuth angle operational method comprises: acquiring audio signals in multiple directions in a space (310); performing echo cancellation processing on the audio signals, wherein the audio signal comprises a target audio direct signal (330); acquiring weight values of multiple time-frequency points in the audio signal by means of the features of the audio signal, wherein the weight value of each time-frequency point indicates the relative ratio of the target audio direct signal to the audio signal at the time-frequency point (350; 370); with regard to the audio signal in each of the multiple directions, respectively weighting the time-frequency components of the audio signal at the multiple time-frequency points by means of the weight values of the multiple time-frequency points to obtain weighted signal energy of the audio signal in each direction (380); and obtaining, by means of the weighted signal energy of the audio signal in each direction, a sound source azimuth angle corresponding to the target audio direct signal in the audio signal (390).
(FR)
L'invention concerne un procédé de fonctionnement d'angle d'azimut de source sonore, un procédé et un appareil destiné à un dispositif interactif audio permettant de positionner un contenu audio cible, ainsi qu'un dispositif interactif audio. Le procédé de fonctionnement d'angle d'azimut de source sonore consiste : à acquérir des signaux audio dans de multiples directions dans un espace (310) ; à effectuer un traitement d'annulation d'écho sur les signaux audio, le signal audio comprenant un signal audio direct cible (330) ; à acquérir des valeurs de pondération de multiples points temps-fréquence dans le signal audio au moyen des caractéristiques du signal audio, la valeur de pondération de chaque point temps-fréquence indiquant le rapport relatif du signal audio direct cible au signal audio au point temps-fréquence (350 ; 370) ; par rapport au signal audio dans chacune des multiples directions, à pondérer respectivement les composantes temps-fréquence du signal audio aux multiples points temps-fréquence au moyen des valeurs de pondération des multiples points temps-fréquence afin d'obtenir une énergie de signal pondérée du signal audio dans chaque direction (380) ; et à obtenir, au moyen de l'énergie de signal pondérée du signal audio dans chaque direction, un angle d'azimut de source sonore correspondant au signal audio direct cible dans le signal audio (390).
(ZH)
一种声源方位角运算方法、音频交互设备定位目标音频的方法、装置和音频交互设备,声源方位角运算方法包括:获取空间中的多个方向上的音频信号(310);对音频信号进行消回声处理,音频信号包括目标音频直射信号(330);利用音频信号的特征,获取音频信号中,多个时频点的权值,每个时频点的权值指示在时频点处目标音频直射信号在音频信号中的相对比重(350;370);对多个方向中各方向上的音频信号,利用多个时频点的权值对音频信号在多个时频点的时频分量分别进行加权,获得各方向上音频信号的加权信号能量(380);利用各方向上音频信号的加权信号能量,获得音频信号中目标音频直射信号对应的声源方位角(390)。
Also published as
Latest bibliographic data on file with the International Bureau