Non-native speech recognition system and method thereof

A speech recognition, non-native language technology, applied in speech recognition, speech analysis, instruments, etc., to achieve the effect of improving recognition performance and increasing computing speed

Inactive Publication Date: 2010-02-17
INST OF ACOUSTICS CHINESE ACAD OF SCI +1
View PDF0 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although adaptive technology has contributed to improving the performance of non-native speech recognition, the performance of the model after adaptation in non-native speech recognition is still lower than that of the native speech model in native speech recognition.

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
  • Non-native speech recognition system and method thereof
  • Non-native speech recognition system and method thereof
  • Non-native speech recognition system and method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The specific embodiment of the present invention is described in further detail below in conjunction with accompanying drawing:

[0039] figure 1 It is the basic principle block diagram of the non-native language speech recognition system based on the mixed model state correction algorithm. It describes the core components of the mixed model state correction algorithm. It mainly consists of several parts: non-native language speech, native / non-native language acoustic model, mandatory Alignment, decoding, state map generation, and decoding of non-native state correction models. figure 2 It is a block diagram of the specific implementation flow of the non-native language speech recognition system based on the mixed model state correction algorithm.

[0040] The core technology of the non-native language speech recognition of the hybrid model state correction algorithm involved in the present invention is the acquisition of the state mapping table (such as figure 2 Mo...

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 a non-native speech recognition system based on mixed model state correction and a method thereof. The non-native speech recognition system comprises a non-native speech interface, a native model module, a non-native model module, a native state decoding module, a non-native state forced alignment module, a native-non-native state similarity matrix computation module, a native-non-native state mapping table computation module and a non-native state correction model decoding module. In the system and the method thereof, a non-native acoustic model is corrected at statelevels based on a native acoustic model of a speaker and state mapping among different models, thus obtaining a model that better meets non-native pronunciation characteristics. The system and the method thereof have the advantages of obvious improvement of recognition performance compared with that of a recognition system which is not corrected by the method on the premise of only the native training data without increase of any non-native speech training data, no obvious speed fall of the recognition speech of the system and very high practicability.

Description

technical field [0001] The invention relates to a speech recognition system and method, in particular to a non-native language speech recognition system and method based on mixed model state correction. Background technique [0002] With the globalization of information in modern society, non-native language speech recognition has become one of the research hotspots in the field of speech recognition technology. For non-native speech recognition, the recognition performance will be greatly reduced compared to native speech recognition, especially for speakers with severe accents. How to improve the performance of non-native language speech recognition with different accents under the premise of ensuring that the speech recognition system has only a small amount of non-native language training data is the focus of non-native language speech recognition research. [0003] Literature (Bohn, O.-S., Flege, J.E., "The production of new and similar vows by adult German learners of...

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): G10L15/06G10L15/065G10L17/06
Inventor 颜永红潘接林张晴晴
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI
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