Pronunciation evaluating method based on voice identification and voice analysis

A speech analysis and speech recognition technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of inaccurate pronunciation, limited teaching effect, inaudible, etc., and achieve the effect of improving accuracy and effect

Active Publication Date: 2006-03-22
BEIJING KEXIN TECH +1
View PDF1 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patented system helps users identify their own tone or issue with speech more easily than others without having any technical means for comparing it yourself. It also analyzes its differences based on specific features like pitching patterns, speaking speed, etc., allowing users to make informed decisions about improving their performance through this analysis process.

Problems solved by technology

The technical problem addressed in this patented text relates how accurate testing for specific phrases like phonetic transcription has been achieved through existing methods that rely heavily on linguistic analysis techniques alone without taking into account any other factors affecting their performance.

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 evaluating method based on voice identification and voice analysis
  • Pronunciation evaluating method based on voice identification and voice analysis
  • Pronunciation evaluating method based on voice identification and voice analysis

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0036] figure 1 It is a system block diagram of the pronunciation evaluation method of this embodiment. As shown in the figure, the pronunciation evaluation system of this embodiment includes a speech feature extraction module, a speech recognition and automatic alignment module, and an information fusion analysis module. After the original voice is input, it first enters the voice feature extraction module for feature extraction. The feature extraction process is to process the original voice signal in frames and obtain the data of each frame's pronunciation intensity, pronunciation duration, fundamental frequency curve and other characteristics. Then perform MFCC transformation on the original speech signal and enter the speech recognition module. According to the current learning content and standard speech model, the speech signal after MFCC transformation is speech recognized and automatically aligned, and the matching can be accurate to every English word in the sentence....

no. 2 example

[0072] The main difference between this embodiment and the first embodiment is that this embodiment also evaluates the pronunciation authenticity of syllables to more accurately point out the difference between the user's pronunciation and the standard pronunciation. In addition, this embodiment uses a different scoring method .

[0073] The pronunciation evaluation system of the present embodiment is the same as the first embodiment, and its method flow includes the following steps:

[0074] Step 200, the user reads a sentence in the learning content;

[0075] Step 201, collect the original voice signal, and convert the analog signal uttered by the user into a digital sampling signal;

[0076] Step 202, the digital signal of voice is processed by frame, usually with 25ms as the length of an analysis frame, after each frame is analyzed, the analysis frame is moved backward by 10ms, and then the processing is repeated until all signal processing is completed;

[0077] Step 20...

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 pronunciation evaluating method based on voice identification and voice analysis includes the following steps: selecting input original phonetic signal, acquiring and converting into digital signal and frame dividing treatment; extracting characteristic parameter of the phonetic frame; identifying the input voice with voice identifying engine to obtain the sectional information of each word and/or syllable and calculating confidence of each word; and evaluating pronunciation truth of each word and/or syllable in input voice based on the confidence of each word and/or syllable. Further, the time length, energy and frequency information of each phonetic frequency may be calculated simultaneously and compared with those in standard pronunciation library, so as to calculate the similarity of each word and/or syllable, and the similarity may be weighted and added to the confidence to obtain the pronunciation truth. The present invention has greatly raised pronunciation evaluating precision.

Description

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

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
Owner BEIJING KEXIN TECH
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