Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2017177629) FAR-TALKING VOICE RECOGNITION METHOD AND DEVICE
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2017/177629 International Application No.: PCT/CN2016/101053
Publication Date: 19.10.2017 International Filing Date: 30.09.2016
IPC:
G10L 15/065 (2013.01) ,G10L 15/08 (2006.01) ,G10L 15/06 (2013.01)
G PHYSICS
10
MUSICAL INSTRUMENTS; ACOUSTICS
L
SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15
Speech recognition
06
Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
065
Adaptation
G PHYSICS
10
MUSICAL INSTRUMENTS; ACOUSTICS
L
SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15
Speech recognition
08
Speech classification or search
G PHYSICS
10
MUSICAL INSTRUMENTS; ACOUSTICS
L
SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15
Speech recognition
06
Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
Applicants:
乐视控股(北京)有限公司 LE HOLDINGS (BEIJING) CO., LTD. [CN/CN]; 中国北京市 朝阳区姚家园路105号3号楼10层1102 Room 1102, 10 Floor, Building 3, 105 Yaojiayuan Road, ChaoYang District Beijing 100025, CN
乐视致新电子科技(天津)有限公司 LE SHI ZHI XIN ELECTRONIC TECHNOLOGY (TIANJIN) LIMITED [CN/CN]; 中国北京市 朝阳区姚家园路105号宏城鑫泰大厦10层 10th layer Hong Cheng Xin Tai Building, No.105 Yaojiayuan Road, ChaoYang District Beijing 100025, CN
Inventors:
那兴宇 NA, Xingyu; CN
Agent:
北京国昊天诚知识产权代理有限公司 CO-HORIZON INTELLECTUAL PROPERTY INC.; 中国北京市 朝阳区小关北里甲2号渔阳置业大厦B座605 Suite 605, B Block, Yuyang Mansion, No.2, Xiaoguanbeili, Chaoyang District Beijing 100029, CN
Priority Data:
201610219407.211.04.2016CN
Title (EN) FAR-TALKING VOICE RECOGNITION METHOD AND DEVICE
(FR) PROCÉDÉ ET DISPOSITIF DE RECONNAISSANCE VOCALE DE CONVERSATION ÉLOIGNÉE
(ZH) 远讲语音识别方法及装置
Abstract:
(EN) A far-talking voice recognition method and device. The method comprises: obtaining a test far-talking voice frame of far-talking voice input from a user, and invoking a pre-trained close-talking voice model to recognize the test far-talking voice frame, so as to obtain a primary recognition result (110); calculating an environment characteristic mapping matrix between the far-talking voice input and close-talking voice input in the current environment according to the primary recognition result (120); mapping, when the far-talking voice input from the user is detected, the far-talking voice input to corresponding approximate close-talking voice input according to the environment characteristic mapping matrix (130); and invoking the pre-trained close-talking voice model to recognize the approximate close-talking voice input, so as to obtain a far-talking voice recognition result (140). Therefore, far-talking voice recognition is achieved with high accuracy.
(FR) L'invention concerne un procédé et un dispositif de reconnaissance vocale de conversation éloignée. Le procédé consiste : à obtenir une trame vocale de conversation éloignée de test d'une entrée vocale de conversation éloignée d'un utilisateur, et à invoquer un modèle vocal de conversation proche pré-appris pour reconnaître la trame vocale de conversation éloignée de test, de façon à obtenir un résultat de reconnaissance primaire (110) ; à calculer une matrice de mappage de caractéristique d'environnement entre l'entrée vocale de conversation éloignée et l'entrée vocale de conversation proche dans l'environnement actuel selon le résultat de reconnaissance primaire (120) ; à mettre en correspondance, lorsque l'entrée vocale de conversation éloignée de l'utilisateur est détectée, l'entrée vocale de conversation éloignée avec une entrée vocale de conversation proche approximative correspondante selon la matrice de mappage de caractéristique d'environnement (130) ; et à invoquer le modèle vocal de conversation proche pré-appris pour reconnaître l'entrée vocale de conversation proche approximative, de façon à obtenir un résultat de reconnaissance vocale de conversation éloignée (140). Par conséquent, une reconnaissance vocale de conversation éloignée est obtenue avec une grande précision.
(ZH) 一种远讲语音识别方法及装置,该方法包括:获取用户远讲语音输入的测试远讲语音帧,调用预先训练的近讲语音模型识别测试远讲语音帧并得到初识结果(110);根据初识结果计算当前环境下远讲语音输入与近讲语音输入的环境特征映射矩阵(120);检测到用户的远讲语音输入时,根据环境特征映射矩阵将远讲语音输入映射至对应的近似近讲语音输入(130);调用预先训练的近讲语音模型识别近似近讲语音输入得到远讲语音识别结果(140)。从而实现了高正确率的远讲语音识别。
front page image
Designated States: AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JP, KE, KG, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW
African Regional Intellectual Property Organization (ARIPO) (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
Eurasian Patent Office (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (EPO) (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG)
Publication Language: Chinese (ZH)
Filing Language: Chinese (ZH)