Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD AND DEVICE FOR SPEECH RECOGNITION, TERMINAL AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/135611
Kind Code:
A1
Abstract:
An artificial intelligence based method and device for speech recognition, a terminal and a storage medium. The method comprises: acquiring a target speech signal to be recognized (S301); determining a target language type of the target speech signal (S302); and by means of a real-time speech recognition model corresponding to the target language type, outputting text information of the target speech signal (S303), wherein the real-time speech recognition model is obtained by training a training set comprising an original speech signal and an extended speech signal, and the extended speech signal is obtained on the basis of conversion of existing text of a basic language type. The method can increase the number of samples needed for training the real-time speech recognition model of a non-basic language, and improve the accuracy and applicability of speech recognition.

Inventors:
GENG JIE (CN)
Application Number:
PCT/CN2020/125608
Publication Date:
July 08, 2021
Filing Date:
October 30, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G10L15/06; G10L15/00
Foreign References:
CN111261144A2020-06-09
CN107731228A2018-02-23
CN109003601A2018-12-14
CN110148400A2019-08-20
CN110473523A2019-11-19
CN110148403A2019-08-20
CN110197658A2019-09-03
US20130070928A12013-03-21
US20170162194A12017-06-08
CN107945792A2018-04-20
CN201911409041A2019-12-31
Other References:
See also references of EP 4064276A4
Attorney, Agent or Firm:
SHENZHEN ZHONGYI UNION INTELLECTUAL PROPERTY AGENCY CO.,LTD. (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: MICROWAVE ABLATION ANTENNA BASED ON SPIRAL SLIT STRUCTURE

Next Patent: WRIST-WORN DEVICE AND WATCHBAND THEREOF