Processing

Please wait...

Settings

Settings

Goto Application

1. CN109378006 - Cross-device voiceprint recognition method and system

Office China
Application Number 201811620418.7
Application Date 28.12.2018
Publication Number 109378006
Publication Date 22.02.2019
Publication Kind A
IPC
G10L 17/24
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
17Speaker identification or verification
22Interactive procedures; Man-machine interfaces
24 the user being prompted to utter a password or a predefined phrase
G10L 17/22
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
17Speaker identification or verification
22Interactive procedures; Man-machine interfaces
G10L 17/04
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
17Speaker identification or verification
04Training, enrolment or model building
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 dialog
CPC
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 17/04
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
17Speaker identification or verification
04Training, enrolment or model building
G10L 17/22
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
17Speaker identification or verification
22Interactive procedures; Man-machine interfaces
G10L 17/24
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
17Speaker identification or verification
22Interactive procedures; Man-machine interfaces
24the user being prompted to utter a password or a predefined phrase
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 SAMSUNG ELECTRONICS (CHINA) R&D CENTER
三星电子(中国)研发中心
SAMSUNG ELECTRONICS CO., LTD.
三星电子株式会社
Inventors WU YONGCHAO
武永超
CHEN JIE
陈洁
Agents 北京德琦知识产权代理有限公司 11018
北京德琦知识产权代理有限公司 11018
Title
(EN) Cross-device voiceprint recognition method and system
(ZH) 一种跨设备声纹识别方法及系统
Abstract
(EN)
The present invention discloses a cross-device voiceprint recognition method and system. The method includes the following steps that: a voiceprint mapping model between different devices is established; voiceprints are extracted from voices recorded by the first device, and voiceprint registration is performed; voiceprint features are extracted from a voice instruction recorded by the second device, and the voiceprint features are mapped to voiceprints registered by another device based on the established voiceprint mapping model, a corresponding user ID is identified; and user data corresponding to the user ID are operated according to the voice instruction, and voice control is completed. With the cross-device voiceprint recognition method and system provided by the technical schemes ofthe present invention adopted, the accuracy of cross-device voiceprint recognition can be improved.

(ZH)
本申请公开了一种跨设备声纹识别方法和系统,包括:建立不同设备之间的声纹映射模型;从第一设备收录的语音中提取声纹,进行声纹注册;从第二设备收录的语音指令中提取声纹特征,基于所建立的声纹映射模型将所述声纹特征映射到通过其他设备注册的声纹,识别出对应的用户ID;根据所述语音指令操作所述用户ID对应的用户数据,完成语音控制。应用本申请公开的技术方案,能够提高跨设备声纹识别的准确率。

Also published as