Voice learning system and method

A technology of speech learning and speech, applied in speech analysis, instruments, electrical digital data processing, etc., can solve the problems of reduced sensitivity of foreign language speech perception, lack of speech training, and ineffective cooperation of speech input, so as to alleviate the problem of foreign language accent , the effect of correcting speech errors

Active Publication Date: 2019-02-22
XI AN JIAOTONG UNIV
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the difficulty of phonetic learning is that the brain's sensitivity to foreign language phonetic perception is reduced from the perspective of the learner itself; from the perspective of the external phonetic learning environment, phonetic input cannot effectively match the laws of the brain's phonetic perception
[0003] The existing pronunciation learning system only evaluates the pronunciation of learners, but does not train the pronunciation itself, so that learners cannot correct pronunciation errors independently

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 learning system and method
  • Voice learning system and method
  • Voice learning system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0054] Firstly, the acoustic features of the speech that are important to distinguish the acoustic elements of the target contrast speech are expanded. For each group of speech to be learned, it is necessary to determine the specific physical parameters of natural sound processing according to the distinguishing elements of the acoustic features of the two speeches.

[0055] After the natural recording is obtained by the speech acquisition module 4 in the corpus production unit 1, it is sent to the speech processing module 5, and the spectral features in the sound are amplified in three different degrees by the MATLAB-based sound processing sub-module 14, respectively 300%, 208 %, 144%, and then make four grades of learning corpus together with the original voice. For example, in English speech / r-l / pair, the three parameters are F3 separation frequency, F3 bandwidth, and F3 transition time. During the synthesis process, the formant frequency difference of / r−l / is amplified ...

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 belongs to the technical field of sound processing and particularly relates to a voice learning system and method. According to an existing voice learning system, a learner cannot autonomously correct voice errors. The invention provides a voice learning system comprising a corpus production unit, the corpus production unit is connected to a voice learning unit, and the voice learning unit is connected to a voice testing unit. The corpus production unit comprises a voice acquisition module which is connected to a voice processing module, and the voice processing module is connected to a video editing module. The voice learning unit comprises a database module, the database module comprises a login sub module which is connected to an icon display sub module, and the icon display sub module is connected to a pronunciation sub module. The voice testing unit comprises a voice icon testing module which is connected to a pronunciation testing module which is connected to a correctness and error judgment module. The voice learning system can correct a voice error of the learner.

Description

technical field [0001] The present application belongs to the technical field of sound processing, and in particular relates to a speech learning system and method. Background technique [0002] Speech is the sound of language, and it is the carrier of the language symbol system. Language relies on sound to realize its social functions. Speech is the sound with distinguishing functions produced by the human vocal organs, and it is the symbol system that most directly records thinking activities. Therefore, although language is a kind of sound, it is essentially different from ordinary sounds. Phonics learning is the foundation of language learning. Studies have shown that babies gradually lose their sensitivity to non-native language sounds after 12 months, which will cause obstacles to foreign language learning in the future. Due to the insensitivity to non-native language speech, learners cannot fully accept the speech information from the auditory sense, so the brains ...

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): G10L25/51G09B5/06G06F3/0481
CPCG06F3/04817G09B5/06G10L25/51
Inventor 程冰
Owner XI AN JIAOTONG UNIV
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