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

Voice recognition method, device and system

A technology for speech recognition and recognition results, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as low keyword coverage, slow keyword search speed, and no similar keyword searches are involved, so as to improve the recognition speed and The effect of coverage

Active Publication Date: 2014-01-08
CHINA UNITED NETWORK COMM GRP CO LTD
View PDF5 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the prior art, since the speech data is first converted into text, and then the keywords are searched by using the text matching method, and there is no search for similar keywords, resulting in slow keyword search speed and low keyword coverage

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, device and system
  • Voice recognition method, device and system
  • Voice recognition method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] figure 1 It is a flowchart of a voice recognition method provided in Embodiment 1 of the present invention. The embodiment of the present invention is suitable for a speech keyword recognition method based on a phoneme map. The speech file is recognized as a phoneme map through acoustics, search keywords are converted into phoneme strings, and the phoneme string is matched and searched in the phoneme map. The specific speech recognition process includes :

[0027] Step 101: Perform acoustic recognition on the voice file to be recognized to obtain a corresponding phoneme map, and convert the search keyword into a phoneme string;

[0028] Phoneme is the smallest phonetic unit divided according to the natural attributes of the speech. From the perspective of acoustic properties, phoneme is the smallest phonetic unit divided from the perspective of sound quality. The sound produced by the same pronunciation action is the same phoneme, and the sounds produced by different pronunc...

Embodiment 2

[0035] figure 2 This is a flowchart of the voice recognition method provided in the second embodiment of the present invention. In the first embodiment, the matching search in the phoneme map according to the phoneme string may be based on the dynamic programming principle or the synchronization principle based on statistical knowledge to search the phoneme string in the phoneme map. For example, the preferred matching search method is phoneme string search based on the principle of dynamic programming.

[0036] Such as figure 2 As shown, on the basis of the first embodiment, by calculating the confidence of each candidate keyword and comparing it with the preset confidence threshold, after obtaining the recognition result, as shown in step 104, according to the recognition result For the confidence of each candidate keyword, the recognition results are sorted, so that the recognition results of triples corresponding to each candidate keyword are arranged in an orderly manner. ...

Embodiment 3

[0040] image 3 It is a block diagram of a speech recognition method provided in Embodiment 3 of the present invention. Such as image 3 As shown, this embodiment can specifically adopt the voice recognition method provided in the foregoing embodiment to realize keyword recognition of voice files. The specific recognition process is as follows:

[0041] Step 301: Perform acoustic recognition on the input voice file;

[0042] Convert the input voice file into phoneme map through acoustic recognition technology.

[0043] Step 302: Input keyword text;

[0044] The entered keyword text is the keyword that will be searched in the voice file.

[0045] Step 303: Convert into phonemes;

[0046] Convert the input keyword text into phonemes to form phoneme strings.

[0047] Step 304: Search for phoneme strings based on the principle of dynamic programming;

[0048] In the phoneme map converted from the speech file, the phoneme string corresponding to the search keyword is matched based on the princ...

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 provides a voice recognition method, device and system. The voice recognition method comprises the following steps of carrying out acoustic recognition on a voice file to be recognized to obtain a corresponding phonemic chart, and converting a search keyword into a phonemic string; carrying out matching search on the phonemic string according to the phonemic string to obtain a keyword candidate list, wherein the keyword candidate list comprises a plurality of candidate keywords similar to the search keyword; obtaining the confidence coefficient of each candidate keyword, and obtaining a recognition result according to a preset confidence coefficient threshold, wherein the recognition result comprises the recognition of the voice file, the inner offset of a file corresponding to the candidate keyword with the confidence coefficient higher than the confidence coefficient threshold, and the confidence coefficient corresponding to the candidate keyword. According to the voice recognition method, device and system provided by the invention, the speed of recognition to the voice keywords and the coverage rate can be increased.

Description

Technical field [0001] The present invention relates to communication technology, in particular to a voice recognition method, device and system. Background technique [0002] With the development of society, information security has become the focus of attention of all countries, especially the monitoring of audio and video content. Sensitive information is detected from the monitored audio and video content to provide a reference for information security. [0003] The recognition of voice data usually adopts audio and video separation of audio and video content, converts the separated voice data into text, and uses text matching to match search keywords in the text. [0004] In the prior art, since the voice data is first converted into text, and then keywords are searched by text matching, and there is no search for similar keywords, the search speed of keywords is slow and the coverage of keywords is low. Summary of the invention [0005] The invention provides a speech recogniti...

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): G10L15/28
Inventor 肖征荣张丽云贾佳廖军严斌峰
Owner CHINA UNITED NETWORK COMM GRP CO LTD
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com