Voice recognition model training method and device, electronic equipment and storage medium

A speech recognition model and training method technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as time-consuming and expensive, and achieve the effect of improving training efficiency and effect and optimizing neural network model

Pending Publication Date: 2020-06-30
THE FOURTH PARADIGM BEIJING TECH CO LTD
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, since the entire training process takes a long time, and currently the number of training rounds and steps are estimated by manual experience to determine whether the

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
  • Voice recognition model training method and device, electronic equipment and storage medium
  • Voice recognition model training method and device, electronic equipment and storage medium
  • Voice recognition model training method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to more clearly understand the above objects, features and advantages of the present disclosure, the present disclosure will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the described embodiments are some of the embodiments of the present disclosure, but not all of the embodiments. The specific embodiments described here are only used to explain the present disclosure, but not to limit the present disclosure. All other embodiments obtained by persons of ordinary skill in the art based on the described embodiments of the present disclosure belong to the protection scope of the present disclosure.

[0034] It should be noted that in this article, relative terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these No such actual relationship or order exists between entities...

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 embodiment of the invention relates to a voice recognition model training method and device, electronic equipment and a storage medium, and is applied to a DNN-HMM voice recognition framework. Themethod includes the steps of obtaining voice data; extracting features of the voice data; performing multi-branch alignment labeling on the voice data based on the features; based on the multi-branchalignment annotation, selecting an alignment annotation result; based on the selected alignment labeling result, performing total training on the neural network to obtain a neural network model; andobtaining a voice recognition model based on the neural network model and the language model. In the embodiment of the invention, through multi-branch alignment annotation and selection of the alignment annotation result, the trained neural network model is optimized, manual intervention is not needed, and the training efficiency and effect are improved.

Description

technical field [0001] Embodiments of the present disclosure relate to the technical field of speech recognition, and in particular to a speech recognition model training method, device, electronic equipment, and storage medium. Background technique [0002] Speech recognition technology is a technology for machines to convert speech signals into corresponding text or commands through the process of recognition and understanding. At present, the training of the speech recognition model under the DNN-HMM speech recognition framework includes three parts: feature extraction, alignment labeling, and neural network training. Among them, the alignment labeling is completed through feature transformation and alignment training, and the determined input and Output; Neural network training is based on input and output, and the neural network model is obtained after the neural network training; the final model obtained by combining the neural network model and the language model is t...

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
IPC IPC(8): G10L15/06G10L15/02G10L15/14G10L15/16G10L15/18
CPCG10L15/063G10L15/02G10L15/16G10L15/144G10L15/18
Inventor 王靖淞涂威威
Owner THE FOURTH PARADIGM BEIJING TECH 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