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

Voice correction fusion technology

A voice and technology technology, applied in the field of voice correction and fusion, can solve the problem of inaccurate recognition of voice recognition technology, and achieve the effect of removing the impact

Active Publication Date: 2020-12-04
AVIC HUADONG OPTOELECTRONICS (SHANGHAI) CO LTD
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of inaccurate recognition of existing speech recognition technology

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 correction fusion technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] Refer to attached figure 1 , a kind of voice correction and fusion technology of the present embodiment, collects the voice data and video data of the speaker at the same time, carries out punctuation preprocessing to the mouth shape collected in the video data, marks the six points inside the lips with letters, and performs preprocessing Afterwards, the image is measured and the lip change angle is calculated through the positions of six points, the voice recognition result is obtained by comparing the sound data with the audio database, and the lip language recognition result is obtained by comparing the lip change angle with the mouth shape database; when the speech recognition result If the matching degree is the same as that of the lip recognition result, the speech recognition result is preferred; when the matching degree of the speech recognition result and the lip recognition result is different, the lip recognition result is preferred.

[0027] The six points a...

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 invention relates to a voice correction fusion technology, voice data and video data of a speaker are collected at the same time, punctuation preprocessing is conducted on a mouth shape collectedin the video data, six point positions inside a lip are marked with letters, a preprocessed image is measured, the lip change angle is calculated through the positions of the six point positions, thesound data with an audio database are compared to obtain a voice recognition result, and the lip change angle is compared with a mouth shape database to obtain a lip language recognition result; whenthe matching degree of the speech recognition result and the lip language recognition result is the same, the speech recognition result is preferentially selected ; and when the matching degrees of the voice recognition result and the lip language recognition result are different, the lip language recognition result are preferentially selected. On the basis of speech recognition, lip language recognition is added, the influence of accent on speech recognition can be effectively removed, the influence of sound is eliminated through lip language recognition in image recognition, and a pronunciator is recognized more accurately through lips.

Description

technical field [0001] The invention belongs to the technical field of speech recognition, in particular to a speech correction fusion technology. Background technique [0002] With the development of computer and related software and hardware technology, speech recognition technology has been more and more applied in various fields, and its recognition rate is also constantly improving. Under specific conditions such as a quiet environment and standard pronunciation, the recognition rate of the current speech recognition input text system has reached more than 95%. However, if the car or outside noise interference is relatively large and the pronunciation is not standard, the recognition rate will be greatly reduced, so that it cannot achieve practical purposes. If other methods can be used to assist the judgment to improve the accuracy of speech recognition, the practicability of speech recognition will be significantly improved. [0003] The human language cognition pro...

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 Applications(China)
IPC IPC(8): G10L15/25G10L15/26G06F16/61G06F16/71G06K9/00
CPCG10L15/25G10L15/26G06F16/61G06F16/71G06V40/20
Inventor 许召辉马翼平徐淑波陈年生范光宇饶蕾孙焜朱羿孜
Owner AVIC HUADONG OPTOELECTRONICS (SHANGHAI) CO LTD