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

Speech recognition method and device, and readable storage medium

A technology of speech recognition and speech recognition model, applied in speech recognition, speech analysis, instruments, etc., can solve the problem that the recognition accuracy cannot meet user requirements, and achieve the effect of improving the accuracy

Active Publication Date: 2022-01-28
SAIC MOTOR
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the recognition accuracy of existing speech recognition models cannot meet user requirements in specific application scenarios

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
  • Speech recognition method and device, and readable storage medium
  • Speech recognition method and device, and readable storage medium
  • Speech recognition method and device, and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In the prior art, speech recognition models usually require a large amount of learning data, so it often takes a long time for model training before the speech can be accurately recognized. At the same time, in a specific industry application scenario, it is difficult for the speech recognition model to obtain enough learning data in advance, and the speech data often contains professional vocabulary that cannot be covered by the general speech recognition model, resulting in the recognition of words in special fields as pronunciation during speech recognition. Similar conventional terms. Therefore, the recognition accuracy of existing speech recognition models cannot meet user requirements in specific application scenarios.

[0032] In the embodiment of the present invention, the pronunciation sequence to be processed is corrected by using a preset pronunciation map to obtain the second recognition result; the pronunciation map includes a vocabulary list of the target ...

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

A speech recognition method and device, and a readable storage medium, wherein the speech recognition includes: using a preset speech recognition model to recognize speech data to obtain a first recognition result; converting the first recognition result into a to-be-processed Pronunciation sequence: correcting the to-be-processed pronunciation sequence by using a preset pronunciation map to obtain a second recognition result; outputting the second recognition result. By adopting the above solution, the accuracy of speech recognition in a specific field can be rapidly improved.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to a voice recognition method and device, and a readable storage medium. Background technique [0002] Existing speech recognition models usually require a large amount of learning data, so it often takes a long time to train the model before it can accurately recognize speech. At the same time, in a specific industry application scenario, it is difficult for the speech recognition model to obtain enough learning data in advance, and the speech data often contains professional vocabulary that cannot be covered by the general speech recognition model, resulting in the recognition of words in special fields as pronunciation during speech recognition. Similar conventional terms. Therefore, the recognition accuracy of existing speech recognition models cannot meet user requirements in specific application scenarios. Contents of the invention [0003] ...

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): G10L15/06G10L15/28
CPCG10L15/06G10L15/28
Inventor 楼晓俊刘峰陈秋蕾
Owner SAIC MOTOR