Feature compensation method based on rapid noise estimation in speech recognition system

A technology of speech recognition and noise estimation, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of difficult real-time implementation and large amount of calculation, so as to achieve the effect of ensuring accuracy and reducing the amount of calculation

Inactive Publication Date: 2013-03-27
HOHAI UNIV
View PDF1 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the feature compensation method based on VTS has a large amount of calculation, and...

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
  • Feature compensation method based on rapid noise estimation in speech recognition system
  • Feature compensation method based on rapid noise estimation in speech recognition system
  • Feature compensation method based on rapid noise estimation in speech recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] 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.

[0021] Such as figure 1 As shown, a Gaussian mixture model GMM1 with fewer Gaussian units is used to extract noise parameters from noisy test speech; another Gaussian mixture model GMM2 with more Gaussian units is used to model with the estimated single Gaussian noise model Combined to obtain a noisy GMM that matches the current test environment; finally, use the noisy GMM to calculate the posterior probability of the noisy test speech, and use the minimum mean square error method to estimate 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 discloses a feature compensation method based on rapid noise estimation in a speech recognition system. The method is characterized in that noise parameter estimation in the feature compensation is separated from pure speech estimation, and noise estimation and pure speech estimation are achieved through different Gaussian mixture models (GMMs). A GMM containing less Gaussian units is used for extracting noise parameters from a noisy tested speech; another GMM containing more Gaussian units is used for being combined with an estimated single Gaussian noise model to obtain a noisy GMM matched with the current test environment; and finally the noisy GMM is used for calculating the posterior probability of the noisy tested speech and the pure speech feature vector is estimated from the noisy tested speech through the minimum mean square error method. According to the method, estimation accuracy of the pure speech can be guaranteed while the calculated amount is reduced.

Description

technical field [0001] The invention relates to a feature compensation method based on fast noise estimation in a speech recognition system, in particular to quickly estimating noise parameters with a Gaussian mixture model containing less Gaussian units, and using a Gaussian mixture model containing more Gaussian units from the The invention relates to a feature compensation method for estimating a pure speech feature vector in a noisy test speech, which belongs to the technical field of speech recognition. Background technique [0002] At present, the speech recognition system has achieved very good performance in the ideal environment of the laboratory. However, in the actual environment, background noise and channel distortion are often unavoidable, they will cause a serious mismatch between the feature vector extracted in the actual application environment and the pre-trained acoustic model, the performance of the recognizer will deteriorate sharply, and it is even poss...

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): G10L15/20G10L15/14
Inventor 吕勇
Owner HOHAI UNIV
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