Method and system for optimizing speech recognition model

A speech recognition model and optimization method technology, which is applied in speech recognition, speech analysis, instruments, etc., can solve the problems of poor speech recognition model effect, data not taking into account different scenarios, etc., and achieve good results

Active Publication Date: 2022-05-06
AISPEECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to at least solve the problem that the data generated by data enhancement in the prior art does not take into account different scenarios, and the speech recognition model trained with data that deviates greatly from the real data is less effective

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
  • Method and system for optimizing speech recognition model
  • Method and system for optimizing speech recognition model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0021] Such as figure 1 Shown is a flow chart of a method for optimizing a speech recognition model provided by an embodiment of the present invention, including the following steps:

[0022] S11: Divide the original audio in the original audio training set according to speech attributes, and determine multiple audio training subsets of different...

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

An embodiment of the present invention provides a method for optimizing a speech recognition model. The method includes: dividing the original audio in the original audio training set according to the speech attributes, and determining multiple audio training subsets of different dimensions; performing data enhancement on the audio training subsets of each dimension according to the data simulation algorithm corresponding to each dimension , generate multiple enhanced audio training sets of different dimensions; train the speech recognition model based on the original audio training set and the multiple enhanced audio training sets, so as to optimize the speech recognition model. The embodiment of the present invention also provides a speech recognition model optimization system. The speech recognition model trained in the embodiment of the present invention can match the requirements of the speech recognition system in different scenarios, and improve the effect of speech recognition.

Description

technical field [0001] The invention relates to the field of speech recognition, in particular to a method and system for optimizing a speech recognition model. Background technique [0002] In order to improve the recognition effect of the speech recognition model, it is necessary to provide a certain amount of audio data for further training. Under the condition of given limited audio data, use the data simulation algorithm to generate analog data that is similar to but different from the existing audio. A large amount of audio data is used to train the speech recognition system, thereby improving the recognition effect of the speech recognition model. [0003] In the process of realizing the present invention, the inventors have found that there are at least the following problems in the related art: [0004] For a given original audio, one data augmentation method is often used, without optimization for different application scenarios of the speech recognition system, a...

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): G10L15/06
CPCG10L15/063
Inventor 李旭
Owner AISPEECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap