Speech recognition method, device, system and language exchange system

A speech recognition and language technology, which is applied in speech recognition, speech analysis, instruments, etc., can solve the problems such as the inability to improve the efficiency and accuracy of speech recognition, and achieve the requirements of reducing the use of programs and capacity, high recognition accuracy, and recognition speed. and improved accuracy

Active Publication Date: 2015-12-09
孔繁泽
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a speech recognition device to solve the technical problem that the efficiency and accuracy of speech recognition cannot be improved under the existing acoustic model

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
  • Speech recognition method, device, system and language exchange system
  • Speech recognition method, device, system and language exchange system
  • Speech recognition method, device, system and language exchange system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In the following embodiments, Chinese is used as the first language for description. The pronunciation of Chinese, according to the standards promulgated by the Ministry of Education, includes 395 atonal Chinese syllables and 1332 toned syllables in Chinese, considering that local dialects also include a similar number of dialect syllables. Chinese is different from the phonemic pronunciation of Slavic languages, and also different from the syllable pronunciation of Korean, Japanese and other languages, but strictly follows the Chinese pronunciation of "initial + final + tone = morpheme sound (syllable sound)". In the Chinese phonetic structure, a group of phonemes has only one loudest central syllable, and the center of each syllable corresponds to the pronunciation of a Chinese character, a syllable corresponds to a morpheme, and a morpheme corresponds to a Chinese character. It should be noted that, due to the phonetic characteristics of Chinese, the solution of the ...

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 relates to the technical field of voice recognition, and provides a voice recognition device, comprising a phoneme storage unit used for storing first language phoneme characteristic data; a phoneme converting unit used for converting a received phoneme signal sequence into a first language phoneme through the first language phoneme characteristic data; a digital coding unit used for coding the first language phoneme uniquely, and forming a first language phoneme coding sequence; a word pronunciation coding sequence and a vocabulary pronunciation coding sequence used for forming the first language by using the first language phoneme coding sequence; a word storage unit used for storing the word, vocabulary or graph of the first language and the corresponding coding sequence; a word converting unit used for generating the word, vocabulary, graph and / or the combination thereof of the first language according to the corresponding relationship of the coding sequence. The invention also discloses a voice recognition system and a language switching system of the voice recognition device. The invention can reduce the equipment cost of voice recognition and improve the recognition accuracy.

Description

technical field [0001] The present invention relates to speech recognition technology, in particular to a method, device, system for speech recognition and a system for realizing language exchange from one language to another. Background technique [0002] Research on speech recognition began in the 1950s, and the Audry system in 1952 was the first speech recognition system that could recognize 10 English digits. In 1959, digital computers were used to identify English vowels and isolated words, and computer speech recognition began. In the 1960s, the endpoint detection of speech end points and dynamic programming significantly improved the level of speech recognition. In the 1970s, signal linear prediction coding ( LPC) technology and dynamic time warping (DTW) technology effectively solve the problem of speech signal feature extraction and unequal-length speech matching. At the same time, vector quantization (VQ) and hidden Markov model (HMM) theories have also entered exp...

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 Patents(China)
IPC IPC(8): G10L15/26
Inventor 孔繁泽
Owner 孔繁泽
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