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

Chinese-English mixed speech recognition method, device, electronic equipment and storage medium

A technology of mixing speech and recognition methods, applied in the computer field, can solve the problems of poor recognition effect and little difference in language model discrimination, and achieve the effect of improving the overall recognition effect

Active Publication Date: 2021-09-03
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the relationship between words with Chinese homonyms, and at the same time, the difference between the language model’s degree of discrimination between such homophonics and English words is not large, resulting in the final speech recognition results not necessarily English words as expected, and the recognition effect is poor. And other issues

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
  • Chinese-English mixed speech recognition method, device, electronic equipment and storage medium
  • Chinese-English mixed speech recognition method, device, electronic equipment and storage medium
  • Chinese-English mixed speech recognition method, device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] 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.

[0035] The Chinese-English mixed speech recognition method, device, electronic equipment and storage medium of the embodiments of the present application are described below with reference to the accompanying drawings.

[0036] figure 1 A schematic diagram of a speech recognition processing procedure 100 according to an embodiment of the present application is shown...

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 application discloses a Chinese-English mixed speech recognition method, device, electronic equipment and storage medium, and relates to the field of artificial intelligence such as the field of speech technology, the field of natural language processing, and the field of deep learning. The specific implementation scheme is: in response to receiving the voice information, determine the pronunciation information and language model score of the voice information; determine whether there are English words in the content of the voice information according to the pronunciation information; The established Chinese-English mapping table determines the Chinese word corresponding to the English word; determines the score of the Chinese word corresponding to the English word, and replaces the score of the English word in the language model score with the score of the Chinese word; according to the replaced language model Score to obtain the speech recognition result for the speech information. The embodiment of the present application can improve the language model score of the path where the Chinese and English words are located, thereby improving the overall recognition effect of Chinese-English mixed speech.

Description

technical field [0001] This application relates to the field of computer technology, especially to the field of artificial intelligence such as speech technology, natural language processing, and deep learning, and specifically to a Chinese-English mixed speech recognition method, device, electronic equipment, and storage medium. Background technique [0002] In many speech recognition applications, there may be situations where Chinese and English are mixed. For example, the content of the speech is "I am very happy that we won this deal; the behavior of this event has a great influence on us;", this kind of homonym is actually based on the English word "deal", which is similar to the English word "deal", such as Diou, Second wait. In related technologies, usually, the mixed Chinese and English speech is directly recognized and scored based on a speech recognition model. However, due to the relationship between words with Chinese homonyms, and at the same time, the differ...

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): G10L15/32G10L15/183G10L15/00
CPCG10L15/32G10L15/183G10L15/005
Inventor 王知践钱胜张奇
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD