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

Voice recognition method and device and electronic equipment

A technology of speech recognition and speech data, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of low speech recognition accuracy and limited promotion of visual information

Pending Publication Date: 2020-09-08
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the splicing method that treats the two kinds of information equally, because the sound information is richer and more distinguishable, will make the acoustic information play a leading role in the recognition results, limiting the promotion of visual information to the recognition results, and the accuracy of speech recognition. still low

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 method and device and electronic equipment
  • Voice recognition method and device and electronic equipment
  • Voice recognition method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0052] One of the core concepts of the embodiments of the present invention is to acquire voice data and other modal data corresponding to voice data and voice data (such as image data of lip movements, image data of sign language movements, image data of related text, etc.), and then based on The attention mechanism fuses speech data and other modal data to realize speech recognition; further, it can effectively fuse different modal information of the same source to obtain more complete fusion information, thereby avoiding the impact of acoustic information on recognition in the prior art. As a result, visual information plays a leading role in limiting the accuracy of recognition results, which improves the accuracy of speech rec...

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 provides a voice recognition method and device and electronic equipment, wherein the method comprises the steps: obtaining voice data and other modal data correspondingto the voice data; and fusing the voice data with other modes based on an attention mechanism, and determining text information corresponding to the voice data. Therefore, different homologous modalinformation can be effectively fused to obtain more complete fusion information, so that the limitation that the accuracy of the recognition result is improved by visual information due to the fact that acoustic information plays a leading role in the recognition result in the prior art can be effectively avoided, and the accuracy of voice recognition is improved.

Description

technical field [0001] The invention relates to the technical field of voice processing, in particular to a voice recognition method, device and electronic equipment. Background technique [0002] With the continuous development of speech recognition technology, speech recognition is applied in more and more fields; for example, smart home can realize voice control based on speech recognition technology, and machine simultaneous interpretation can realize simultaneous interpretation based on speech recognition technology, as well as smart cars The user's voice commands such as navigation, switching air conditioner / music, etc. can be executed based on voice recognition technology. [0003] Usually when the speech environment is relatively quiet, the accuracy of speech recognition will be relatively high, but when the speech environment is relatively noisy, the accuracy of speech recognition will be significantly reduced; therefore in order to improve the accuracy of speech re...

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): G10L15/06G10L15/22G10L15/25G10L15/26G10L19/008
CPCG10L15/063G10L15/22G10L15/26G10L15/25G10L19/008
Inventor 周盼
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD