Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020088153 - SPEECH PROCESSING METHOD AND APPARATUS, STORAGE MEDIUM AND ELECTRONIC DEVICE

Publication Number WO/2020/088153
Publication Date 07.05.2020
International Application No. PCT/CN2019/107578
International Filing Date 24.09.2019
IPC
G10L 21/0208 2013.01
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
CPC
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 21/02
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
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
Applicants
  • OPPO广东移动通信有限公司 GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD. [CN]/[CN]
Inventors
  • 陈岩 CHEN, Yan
Agents
  • 深圳翼盛智成知识产权事务所(普通合伙) ESSEN PATENT&TRADEMARK AGENCY
Priority Data
201811273432.430.10.2018CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) SPEECH PROCESSING METHOD AND APPARATUS, STORAGE MEDIUM AND ELECTRONIC DEVICE
(FR) PROCÉDÉ ET APPAREIL DE TRAITEMENT DE LA PAROLE, SUPPORT DE STOCKAGE ET DISPOSITIF ÉLECTRONIQUE
(ZH) 语音处理方法、装置、存储介质和电子设备
Abstract
(EN)
Disclosed are a speech processing method and apparatus, a storage medium and an electronic device. The speech processing method comprises: acquiring original speech (101); if the original speech is reverberated speech, inputting the original speech into a generative sub-model of a pre-trained generative adversarial network model, wherein the generative sub-model is used for carrying out de-reverberation processing on the original speech (102); and determining output speech of the generative sub-model to be de-reverberated speech (103).
(FR)
Cette invention concerne un procédé et un appareil de traitement de la parole, un support de stockage et un dispositif électronique. Le procédé de traitement de la parole comprend les étapes consistant à : acquérir une parole d'origine (101) ; si la parole d'origine est une parole réverbérée, entrer la parole d'origine dans un sous-modèle génératif d'un modèle de réseau génératif contradictoire pré-entraîné, le sous-modèle génératif étant utilisé pour effectuer un traitement de dé-réverbération sur la parole d'origine (102) ; et définir une parole de sortie du sous-modèle génératif en tant que parole dé-réverbérée (103).
(ZH)
语音处理方法、装置、存储介质和电子设备,其中语音处理方法包括获取原始语音(101),若原始语音为混响语音,则将原始语音输入至预先训练的生成式对抗网络模型的生成子模型,其中,生成子模型用于对原始语音进行去混响处理(102),将生成子模型的输出语音确定为去混响语音(103)。
Also published as
Latest bibliographic data on file with the International Bureau