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

Pronunciation quality evaluation method of computer auxiliary language learning system

A computer-assisted, language learning technology, applied in speech analysis, educational appliances, instruments, etc., can solve the problems of failure to evaluate the pronunciation quality, lack of perceptual distortion of pronunciation quality, etc., and achieve improved robustness, good robustness, and good performance. Effect

Active Publication Date: 2008-08-20
北京华控智加科技有限公司
View PDF1 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing technology fails to evaluate the pronunciation quality at the prosody level, and there is a lack of research on the perceptual distortion of pronunciation quality

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
  • Pronunciation quality evaluation method of computer auxiliary language learning system
  • Pronunciation quality evaluation method of computer auxiliary language learning system
  • Pronunciation quality evaluation method of computer auxiliary language learning system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Embodiments of the pronunciation quality evaluation method for computer-aided language learning proposed by the present invention will be described in detail below with reference to the accompanying drawings. figure 1 is an overall flow chart of the pronunciation quality evaluation method according to the present invention. (1) Firstly, the matching score, perceptual score, segment length score and pitch score are calculated through the acoustic model, perceptual model, segment length model and pitch model for the reference speech and the test speech respectively. (2) Score fusion of these scores describing the quality of pronunciation in terms of acoustics, perception, and prosody, respectively. (3) Use the fused scores to evaluate the pronunciation quality of the test speech.

[0034] The reference utterance refers to the teacher's standard utterance used as a standard for evaluating the utterance quality, and the test utterance refers to the utterance of the learner...

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 present invention belongs to voice field of technology, pronunciation quality evaluation method of computer Computer Aided Language Learning system includes: calculation of the matching fraction, calculation of the sensing fraction based on Mel frequency scale, calculation of the segment length fraction and calculation of the keynote fraction, and processing fusion after mapping the above fractions; the pronunciation quality evaluation method of the invention has better robustness, high pertinency with the expert evaluation, used for interactive language learn and automatic spoken language test.

Description

technical field [0001] The invention belongs to the technical field of speech, and in particular relates to a method for evaluating speech pronunciation quality in a computer-aided language learning system by using speech signal processing technology. Background technique [0002] When learners are learning a language, reliable evaluation of their pronunciation quality is the core function of a computer-aided language learning system. However, due to the limitation of the existing technology, the performance of the current pronunciation quality evaluation method is not ideal enough, and there is still a certain distance from practicality. [0003] At present, the method of evaluating pronunciation quality by computer is mainly based on Hidden Markov Model (HMM). Chinese invention patent application No. 200510114848.8 discloses a pronunciation quality evaluation method for a learning machine. This method uses Hidden Markov Model to train the standard pronunciation model, an...

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): G10L11/00G10L19/00G09B19/04G10L25/60
Inventor 刘加
Owner 北京华控智加科技有限公司
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