Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Robust Speech Recognition Method Based on Multi-Band Feature Compensation

A speech recognition and multi-band technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of speech recognition system performance degradation, acoustic model mismatch, etc., and achieve the effect of improving recognition performance and noise robustness

Active Publication Date: 2019-08-20
HOHAI UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The performance of speech recognition systems tends to degrade in noisy environments because the background noise makes the feature parameters extracted in the test environment not match the pre-trained 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
  • A Robust Speech Recognition Method Based on Multi-Band Feature Compensation
  • A Robust Speech Recognition Method Based on Multi-Band Feature Compensation
  • A Robust Speech Recognition Method Based on Multi-Band Feature Compensation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Below in conjunction with specific embodiment, further illustrate the present invention, should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various equivalent forms of the present invention All modifications fall within the scope defined by the appended claims of the present application.

[0020] A robust speech recognition method based on multi-band feature compensation, the specific steps are as follows:

[0021] (1) The MFCC of the pure training speech is directly decomposed into sub-MFCCs of four frequency bands in the cepstrum domain: MFCC1~MFCC4, and the GMM of this frequency band is generated by training with all the sub-MFCCs of each frequency band, and obtains GMM1~GMM4;

[0022] (2) Acoustic preprocessing and feature extraction are carried out to the noisy input speech to ...

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 robust speech recognition method based on multi-band characteristic compensation, comprising: decomposing MFCC (Mel frequency cepstrum coefficient) extracted in noise environment directly in a cepstrum domain to obtain sub-MFCCs of four bands; then, using a pre-trained Gaussian hybrid model on each band to perform characteristic compensation on the sub-MFCC of the present band to obtain pure sub-characteristic parameters; finally, subjecting the estimated sub-MFCCs of the four bands to characteristic combination to obtain complete MFCC of pure speech. The method can provide improved recognition performance for a speech recognition system in a limited noise environment, and improved noise robustness for the system.

Description

technical field [0001] The invention relates to decomposing the cepstrum feature parameters of speech to be recognized into sub-signals of several frequency bands, respectively performing feature compensation on the sub-signals of each frequency band, and then synthesizing the cepstrum features of each frequency band after compensation into a complete cepstrum feature The invention relates to a parameter multi-band robust feature compensation method, which belongs to the technical field of speech recognition. Background technique [0002] The performance of speech recognition systems tends to degrade in noisy environments because the background noise makes the feature parameters extracted in the test environment mismatch with the pre-trained acoustic model. Therefore, in practical applications, some compensation techniques need to be adopted to reduce the impact of noise on the speech recognition system and improve the recognition rate of the speech recognition system. [0...

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): G10L15/20G10L25/24
Inventor 吕勇
Owner HOHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com