Processing

Please wait...

Settings

Settings

Goto Application

1. WO2019056482 - VOICE KEYWORD IDENTIFICATION METHOD, APPARATUS AND DEVICE AND COMPUTER READABLE STORAGE MEDIUM

Publication Number WO/2019/056482
Publication Date 28.03.2019
International Application No. PCT/CN2017/108233
International Filing Date 30.10.2017
IPC
G10L 15/10 2006.1
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
10using distance or distortion measures between unknown speech and reference templates
G10L 15/14 2006.1
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
14using statistical models, e.g. Hidden Markov Models
G10L 15/22 2006.1
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
22Procedures used during a speech recognition process, e.g. man-machine dialog
G10L 15/26 2006.1
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
26Speech to text systems
CPC
G10L 15/10
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
10using distance or distortion measures between unknown speech and reference templates
G10L 15/14
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
14using statistical models, e.g. Hidden Markov Models [HMMs]
G10L 15/22
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
22Procedures used during a speech recognition process, e.g. man-machine dialogue
G10L 15/26
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
26Speech to text systems
G10L 2015/223
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
22Procedures used during a speech recognition process, e.g. man-machine dialogue
223Execution procedure of a spoken command
Applicants
  • 平安科技(深圳)有限公司 PING AN TECHNOLOGY (SHENZHEN) CO., LTD. [CN]/[CN]
Inventors
  • 查高密 ZHA, Gaomi
  • 程宁 CHENG, Ning
  • 王健宗 WANG, Jianzong
  • 肖京 XIAO, Jing
Agents
  • 深圳市精英专利事务所 SHENZHEN TALENT PATENT SERVICE
Priority Data
201710855490.720.09.2017CN
Publication Language Chinese (zh)
Filing Language Chinese (ZH)
Designated States
Title
(EN) VOICE KEYWORD IDENTIFICATION METHOD, APPARATUS AND DEVICE AND COMPUTER READABLE STORAGE MEDIUM
(FR) PROCÉDÉ, APPAREIL ET DISPOSITIF D'IDENTIFICATION VOCALE DE MOT-CLÉ, ET SUPPORT DE STOCKAGE LISIBLE PAR ORDINATEUR
(ZH) 语音关键词识别方法、装置、设备及计算机可读存储介质
Abstract
(EN) A voice keyword identification method, apparatus and device, and a computer readable storage medium. The voice keyword identification method comprises: receiving an input voice signal (101); extracting audio features in the voice signal (102); calculating, according to the audio features, the probabilities of keywords to an acoustics model, a pronunciation dictionary and a language model by utilizing the acoustics model, the pronunciation dictionary and the language model; determining whether a probability is greater than a threshold; if a probability is greater than the threshold, counting the number of the keywords corresponding to the probability; and if the number of the keywords corresponding to the probability is one, using the keyword corresponding to the probability as a keyword identification result. After the probabilities of possible keywords are calculated, a keyword corresponding to the probability greater than the threshold is used as the keyword identification result, thus improving keyword identification rate.
(FR) L'invention concerne un procédé, un appareil et un dispositif d'identification vocale de mot-clé, ainsi qu'un support de stockage lisible par ordinateur. Le procédé d'identification vocale de mot-clé consiste à : recevoir un signal vocal d'entrée (101) ; extraire des caractéristiques audio dans le signal vocal (102) ; calculer, en fonction des caractéristiques audio, les probabilités de mots-clés par rapport à un modèle acoustique, un dictionnaire de prononciation et un modèle de langue en utilisant le modèle acoustique, le dictionnaire de prononciation et le modèle de langue ; déterminer si une probabilité est ou non supérieure à un seuil ; si une probabilité est supérieure au seuil, compter le nombre des mots-clés correspondant à la probabilité ; et si le nombre des mots-clés correspondant à la probabilité est de un, utiliser le mot-clé correspondant à la probabilité comme résultat d'identification de mot-clé. Après que les probabilités de mots-clés possibles sont calculées, un mot-clé correspondant à la probabilité supérieure au seuil est utilisé comme résultat d'identification de mot-clé, améliorant ainsi le taux d'identification de mot-clé.
(ZH) 一种语音关键词识别方法、装置、设备及计算机可读存储介质。语音关键词识别方法包括:接收输入的语音信号(101);提取语音信号中的音频特征(102);根据音频特征,利用声学模型、发音词典、语言模型计算关键词对于声学模型、发音词典、语言模型的概率;判断概率是否大于阈值,若概率大于阈值,统计概率对应的关键词的数量;若概率对应的关键词的数量为一个,将概率对应的关键词作为关键词识别的结果。当计算出可能的关键词的概率后,将概率中大于阈值的对应的一个关键词作为关键词识别的结果,提高了关键词的识别率。
Related patent documents
Latest bibliographic data on file with the International Bureau