Unlock instant, AI-driven research and patent intelligence for your innovation.

A speech recognition model training method, device and electronic equipment

A speech recognition model and training method technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problem of large workload of model training, and achieve the effect of improving accuracy and reducing workload

Active Publication Date: 2020-12-11
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This application provides a speech recognition model training method, device and electronic equipment to solve the problem of large model training workload

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A speech recognition model training method, device and electronic equipment
  • A speech recognition model training method, device and electronic equipment
  • A speech recognition model training method, device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0113] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0114] Such as figure 1 As shown, according to the embodiments of the present application, the present application provides a speech recognition model training method, which can be applied to electronic devices, such as servers or terminal devices, and the method includes:

[0115] Step S101: Obtain the first syllable label sequence of the audio in the first languag...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a speech recognition model training method and a device, and electronic equipment, and relates to the technical field of machine learning. The speech recognition model trainingmethod comprises the steps of: determining a plurality of differential syllable label sequences from the second syllable label sequence; determining a target differential syllable label sequence according to the plurality of differential syllable label sequences, the target differential syllable label sequence being a union set of the plurality of differential syllable label sequences; generatinga third syllable label sequence according to the target difference syllable label sequence; and performing speech recognition model training according to the first syllable label sequence and the third syllable label sequence to obtain a mixed speech recognition model. The hybrid speech recognition model can be trained according to the first syllable label sequence and the target difference syllable label sequence, and the model training workload is reduced.

Description

technical field [0001] The present application relates to the technical field of machine learning in computer technology, and in particular to a speech recognition model training method, device and electronic equipment. Background technique [0002] With the development of speech recognition technology, the performance of speech recognition has been practical. For example, various input methods on mobile phones have voice interaction functions. However, in practical applications, there are speech recognition in different language scenarios, that is, there are speech recognition in multiple languages, for example, standard Chinese, local Chinese, and for example, standard English, British English, and American English. At present, many voice interaction products support different voice recognition, such as voice recognition options on mobile phone input methods, users can choose the corresponding language according to their needs, and some smart TVs and smart refrigerators de...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G10L15/06G10L15/02G10L15/08G10L15/14G10L25/24
CPCG10L15/02G10L15/063G10L15/08G10L15/14G10L25/24G10L2015/027G10L2015/0631
Inventor 袁胜龙
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD