Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SPEECH RECOGNITION MODEL TRAINING METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2023/245869
Kind Code:
A1
Abstract:
A speech recognition model training method and apparatus, an electronic device (1200), and a storage medium, relating to the technical field of artificial intelligence, and in particular to the fields of deep learning, speech recognition and the like. The method comprises: S201, constructing a negative sample according to a positive sample, so as to obtain a target negative sample used for constraining a speech decoding path; S202, obtaining training data according to the positive sample and the target negative sample; and S203, training a first speech recognition model according to the training data, so as to obtain a second speech recognition model.

More Like This:
JP6110945The method and system of linear discriminant analysis in an automatic voice recognition system to which bias was able to be applied alternatively
JP4876134Speaker recognition
JP2001184084METHOD AND DEVICE FOR VOICE RECOGNITION AND MEDIUM WHERE PROGRAM THEREOF IS RECORDED
Inventors:
YOU LANHUA (CN)
JIA LEI (CN)
ZHANG QI (CN)
JIANG ZHENGXIANG (CN)
Application Number:
PCT/CN2022/116552
Publication Date:
December 28, 2023
Filing Date:
September 01, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BEIJING BAIDU NETCOM SCI & TECH CO LTD (CN)
International Classes:
G10L15/06
Foreign References:
CN114299927A2022-04-08
CN113646833A2021-11-12
CN111418009A2020-07-14
CN113420121A2021-09-21
CN114299933A2022-04-08
US20200043483A12020-02-06
Attorney, Agent or Firm:
BEIJING ELITE IP LAW OFFICE (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: MACROSCOPIC ARRAY ELECTRODE AND PREPARATION METHOD THEREFOR AND USE THEREOF

Next Patent: TRANSVERSE CONNECTION APPARATUS AND RESETTING AND FIXING SYSTEM USING SAME