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

Method for determining and recognizing voice intentions based on automatic classification technology

A technology of automatic classification and speech recognition, applied in speech recognition, speech analysis, instruments, etc., can solve the problem of low accuracy of speech recognition, and achieve the effect of reducing interference and reducing the probability of discarding

Inactive Publication Date: 2013-12-25
GUIYANG SHIJIHENGTONG TECH
View PDF5 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem solved by the present invention is: in order to solve the problem of low speech recognition accuracy, the present invention provides a method of speech intention judgment and recognition based on automatic classification technology , so as to better ensure that the user's intention is judged by voice and further improve the accuracy of voice recognition

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 determining and recognizing voice intentions based on automatic classification technology
  • Method for determining and recognizing voice intentions based on automatic classification technology
  • Method for determining and recognizing voice intentions based on automatic classification technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In order to better understand the present invention, the present invention will be described in more detail below in conjunction with specific embodiments and accompanying drawings. In the following description, when detailed descriptions of existing prior art may obscure the subject matter of the present invention, such descriptions will be omitted here.

[0020] The voice intent judgment and recognition method based on automatic classification technology can be divided into the following two modules:

[0021] The speech recognition module receives incoming speech information, performs noise reduction and feature extraction processing on the input speech, converts the input speech into a feature sequence, and then uses a hidden Markov continuous speech recognizer for speech recognition to convert the speech feature sequence into Word graph network with confidence;

[0022] The intention classification module receives the information processed by the speech recognition...

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 determining and recognizing voice intentions based on an automatic classification technology. The method is characterized in that a voice recognition module is firstly adopted to carry out noise reduction and feature extraction processing on input voices, the input voices are converted into feature sequences, a Hidden Markova Model continuous voice recognizer is adopted for voice recognition, and the voice feature sequences are converted into a word-graph network with a confidence coefficient; then an intention classification module is used for converting the word-graph network of the user voices into a spatial vector with a weight, an intention classifier trained well in the intention classification module is used for automatic intention classification, the voices are converted into the intentions, finally the most correct characters are selected according to the character repertoire field corresponding to the intentions, and the high-accuracy voice recognition is formed.

Description

technical field [0001] The invention relates to a voice intention judgment and recognition method based on automatic classification technology, and belongs to the technical field of voice recognition. Background technique [0002] Speech recognition technology is the basic technology for speech intent determination, which realizes the conversion from speech to text. In recent years, speech recognition technology has developed very rapidly, and the recognition ability has been greatly improved. With the rise of the mobile Internet, speech recognition technology has gradually entered the application market and has become another entrance for mobile applications besides text input. However, these applications are all limited to application scenarios in which the user cooperates, and have high requirements on the stability and input quality of the user's voice input. Due to the characteristics of the user's voice, such as loud accent, loud noise, high narrow-band distortion ra...

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): G10L15/08G10L15/00
Inventor 李建洲杨兴荣
Owner GUIYANG SHIJIHENGTONG 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