Method and device for recognizing personalized speeches

A speech recognition and speech recognition model technology, which is applied in speech recognition, speech analysis, instruments, etc., can solve problems such as poor recognition accuracy, difficulty in describing the differences in speech of different users, and difficulty in meeting the individual needs of users in speech recognition. The effect of improving the accuracy of speech recognition and improving the accuracy of recognition

Active Publication Date: 2013-02-06
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF9 Cites 52 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing technology uses the same speech recognition model to recognize the speech of various users. Due to the same speech recognition model, it is difficult to describe the differences in the

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 and device for recognizing personalized speeches
  • Method and device for recognizing personalized speeches
  • Method and device for recognizing personalized speeches

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0025] Please refer to figure 1 , figure 1 It is a schematic flowchart of the personalized voice recognition method in the present invention. Such as figure 1 As shown, the method includes:

[0026] Step S101: Determine whether the speech to be recognized belongs to an authorized user, if yes, use the speech recognition model corresponding to the authorized user to recognize the speech to be recognized, otherwise execute step S102.

[0027] Step S102: Determine the dialect category of the speech to be recognized, and use the speech recognition model corresponding to the dialect category of the speech to be recognized to recognize the speech to be recognized.

[0028] The above steps are described in detail below.

[0029] The authorized user ...

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 method and a device for recognizing personalized speeches. The method includes: A, determining whether a speech to be recognized belongs to an authorized user or not; if yes, using a speech recognition module corresponding to the authorized user to recognize the speech to be recognized; and if not, executing a step B; B, determining what dialect type the speech to be recognized belongs to, and using a speech recognition module, corresponding to the dialect type which the speech to be recognized belongs to, to recognize the speech to be recognized. Precision in recognizing speeches of various users can be improved by the use of the method and device.

Description

【Technical field】 [0001] The invention relates to speech recognition technology, in particular to a personalized speech recognition method and device. 【Background technique】 [0002] Speech recognition technology has important applications in many fields, such as voice dialing, voice navigation and other applications, all rely on speech recognition technology. The effect of speech recognition directly affects the effect of various applications related to speech recognition. [0003] The ability of the speech recognition model to describe speech to text is a key factor that affects the quality of speech recognition. The existing technology uses the same speech recognition model to recognize the speech of various users. Due to the same speech recognition model, it is difficult to describe the differences in the speech of different users. Therefore, using this method for speech recognition, the recognition accuracy in many cases Poor, it is difficult to meet the individual ne...

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): G10L15/18
Inventor 刘俊启胡星郭志峰
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap