Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for recognizing voice

A speech recognition and speech model technology, applied in the multimedia field, can solve the problems of unreachable, limited data volume, low overall efficiency, etc., and achieve the effect of reducing the recognition error rate, reducing workload, and improving performance

Inactive Publication Date: 2011-07-13
TVMINING BEIJING MEDIA TECH
View PDF9 Cites 76 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the result of speech recognition is far from the level of manual labeling, and the disadvantage of post-processing to assist a large number of manual workers is that the overall efficiency is relatively low, and the amount of data processed at the same time is limited.

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
  • Method for recognizing voice
  • Method for recognizing voice

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and through specific implementation methods.

[0025] The main idea of ​​the technical solution of the present invention is the language model adaptive technology in speech recognition. Language model adaptive technology usually needs to find relevant corpus for interpolation. Because it is difficult to grasp the matching degree with the test news, it is very unstable for performance improvement; if a corpus that is close to an exact match can be found, the recognition rate can reach a very high level, but if If you can find this kind of text corpus, you don't need to recognize it. The purpose of language model adaptation is to reduce the language difference between the model and the recognition task. These differences include dictionary differences, style and content differences, and model probability distribution differences. The most fundamen...

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 discloses a method for recognizing voice. The method comprises the following steps of: acquiring audio data; acquiring a Lattice result of the audio data, wherein the Lattice result comprises time point information, a plurality of pieces of candidate information and matching likelihood scoring information; acquiring confidence scoring information according to the plurality of piecesof candidate information and the matching likelihood scoring information; rearranging the plurality of pieces of candidate information by using a stronger voice model and providing the optimal recognition result; positioning a voicing position corresponding to the audio data and simultaneously displaying other candidate words; selecting or inputting a correct text to finish amendment and freezingthe amended text; and searching a related text training language model by using a search engine according to the amended text serving as a key word, interpolating to acquire an adaptive language model, and returning and newly recognizing the rest part of audio data by using the adaptive voice model. By using the technical scheme, the voice recognition rate can be improved, and the workload of manual checking can be reduced.

Description

technical field [0001] The invention relates to the field of multimedia technology, in particular to a voice recognition method. Background technique [0002] With the development of the information age, audio and video materials are increasing day by day, presenting a massive scale. Compared with other types of content, audio and video content has a more vivid display form and carries richer information. In order to obtain the content of interest conveniently, it is necessary to extract information from these materials. The current method is to use various intelligent analysis methods to extract useful value information from audio and video from various angles, and carry out intelligent information indexing. Among them, the most important technology at present is to use speech recognition to recognize the speech data in the audio and video data, and add text labels to the audio and video according to the recognition results, and the audio and video after the above process...

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): G10L15/00G10L15/183
Inventor 吴鹏刘赵杰
Owner TVMINING BEIJING MEDIA TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com