Supercharge Your Innovation With Domain-Expert AI Agents!

Detection method for mispronounced phonetic symbol and device

A detection method and detection device technology, applied in speech analysis, electrical operation teaching aids, instruments, etc., can solve problems such as low recognition of mispronunciation detection, incorrect pronunciation of sentences or words, and low fluency in equipment use, and improve data quality. The effect of processing efficiency, improving use fluency, and high market application value

Inactive Publication Date: 2019-01-04
美高森(成都)人工智能科技股份有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the existing language learning machine technology has problems such as low detection and recognition of mispronunciation, low data processing efficiency, low equipment use fluency, and low user learning efficiency.
The existing technology can detect sentences and / or words that are mispronounced by the learner, but cannot detect the specific factors represented by the phonetic symbols that are mispronounced by the learner and cause the sentence or word to be mispronounced

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
  • Detection method for mispronounced phonetic symbol and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Such as figure 1 Shown, a kind of detection method of the phonetic symbol that is mispronounced comprises splitting module, is used for sentence processing as follows: sentence is split into chunk group, and described chunk group is split into chunk, sub-chunk , sub-chunk, and sub-chunk, wherein, a sentence can be split into two or more chunks, a chunk can be split into two or more sub-chunks, and a sub-chunk can be split Divide into two or more subchunks, and so on, splitting the sentence down to words, and if the words are disyllabic or polysyllabic, into syllables; then

[0068] For the split sentences, the execution process is based on the language learning machine system:

[0069] S1. The first input is to pre-input the standard pronunciation of the first sentence and its chunk group;

[0070] S2. The second input is to perform voice input on the second sentence and its chunk group;

[0071] S3. Syllable check detection, check the voice input in step S2 with the...

Embodiment 2

[0074] A device for detecting mispronounced syllables, comprising a splitting module for processing sentences as follows: sentences are split into groups of chunks, groups of chunks are split into chunks, subchunks, subchunks, Further sub-chunks, wherein a sentence can be split into two or more chunks, a chunk can be split into two or more sub-chunks, a sub-chunk can be split into two or more Two or more subchunks, and so on, splitting the sentence down to words, or syllables if the words are disyllabic or polysyllabic; then

[0075] For the split sentences, based on the language learning machine system, the following modules are set:

[0076] The first input module is used to pre-input the standard pronunciation of the first sentence and its chunk group;

[0077] The second input module is used for voice input of the second sentence and its chunk group;

[0078] The syllable checking detection module is used to check whether there is a wrong pronunciation by checking the vo...

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 detection method for a mispronounced phonetic symbol and device. The device comprises a dividing module. The dividing module processes a sentence in the following way: the sentence is divided to a block group, the block group is divided to blocks, sub blocks, secondary blocks and sub-secondary blocks. The sentence can be divided to two or more than two blocks; each blockcan be divided to two or more than two sub blocks; each sub block can be divided to two or more than two secondary blocks, and by analogy, the sentence is continuously divided to words, if the word isa disyllabic word or a polysyllabic word, the word is divided to phonetic symbols. The mispronunciation detection and recognition accuracy is enhanced, functions of a language learning device are enhanced, and the learning efficiency of the user is improved.

Description

technical field [0001] The present invention relates to the technical field of speech detection, and more specifically, to a method and device for detecting wrongly pronounced phonetic symbols. Background technique [0002] Pronunciation is an essential element of language learning. In the learning stage of a language, accurate pronunciation often brings confidence to learners, and this confidence will in turn stimulate their interest in learning, and interest is the best teacher. Accurate pronunciation is not only the effect of language learning, but also a sufficient condition for learning a language well. Accurate identification of the phonetic symbols of the learner's mispronunciation is a sufficient condition for the learner to efficiently correct the mispronunciation. [0003] The language learning machine combines the learning characteristics of different languages, and uses computer communication technology, etc., not only to assist users in learning languages ​​fr...

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): G09B5/00G09B7/00G10L25/60
CPCG09B5/00G09B7/00G10L25/60
Inventor 王崝骁
Owner 美高森(成都)人工智能科技股份有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com