Speech recognition system and recognition method thereof

A technology of speech recognition and speech, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of poor real-time performance, achieve the effect of small grouping model library, improve real-time performance and recognition accuracy, and reduce the cost of recognition process

Inactive Publication Date: 2012-11-21
GUANGDONG UNIVERSITY OF FOREIGN STUDIES
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the pattern matching process of the traditional DHMM algorithm, all templates are matched separately. When the number of templates increases, the time consumed by the matching process increases accordingly, that is, when the number of voices to be recognized is large, the real-time performance is poor.

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 system and recognition method thereof
  • Speech recognition system and recognition method thereof
  • Speech recognition system and recognition method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The invention is an operating system for realizing a local speech recognition function on an android operating system. By preprocessing the collected sound signals, the system has higher efficiency and higher recognition accuracy in later stage speech recognition. In the pattern matching process of the traditional DHMM algorithm, all hmm templates are traversed and matched separately (hidden Markov model (HMM) can be described by five elements, including 2 state sets and 3 probability matrices):

[0027] 1. Hidden state S

[0028] These states satisfy the Markov property, which is the state actually implied in the Markov model. These states are usually not available through direct observation. (such as S1, S2, S3, etc.)

[0029] 2. Observable state O

[0030] Associated with the implicit state in the model, it can be obtained through direct observation. (For example, O1, O2, O3, etc., the number of observable states does not necessarily have to be the same as the nu...

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 speech recognition system and a recognition method thereof. The system comprises a speech acquiring module, a speech pretreatment module, a speech feature extraction module, a grouping judgment module and a speech recognition module, wherein the grouping judgment module is used for grouping speeches in a clustering mode; the speech acquiring module is connected with the speech pretreatment module, the speech pretreatment module is connected with the speech feature extraction module, the speech feature extraction module is connected with the grouping judgment module, and the grouping judgment module is connected with the speech recognition module; the grouping judgment module comprises a grouping judgment unit and at least two grouping models; the speech feature extraction module is connected with the grouping judgment unit, and the grouping judgment unit is respectively connected with the at least two grouping models; and the grouping models are connected with the speech recognition module.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to an operating system for realizing a local speech recognition function based on an android operating system. The invention also relates to the speech recognition method of the speech recognition system. Background technique [0002] To implement the speech recognition function in an embedded operating system, it is usually necessary to preprocess the input speech, extract feature parameters, pattern match, and then output. Among them, pattern matching usually adopts the traditional DHMM model for pattern matching, and Zhang Weiqing's "Research on Speech Recognition Algorithms" provides a detailed hidden Markov model. Hidden Markov model (HMM) can be described by five elements, including 2 state sets and 3 probability matrices. Generally, a hidden Markov model can be represented concisely by λ=(A,B,π) triplet husband model. Hidden Markov models are actually extensions...

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): G10L15/02G10L15/14
Inventor 张晶覃本灼
Owner GUANGDONG UNIVERSITY OF FOREIGN STUDIES
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