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

Isolation word identification method based on double-layer GMM structure and VTS feature compensation

A recognition method and technology of isolated words, applied in speech recognition, speech analysis, instruments, etc., can solve the problem of long recognition time of the isolated word recognition system, and achieve the effect of reducing time, overall time and estimation time.

Inactive Publication Date: 2015-09-09
SOUTHEAST UNIV
View PDF5 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the long recognition time of the isolated word recognition system has become a disadvantageous factor for transplanting to embedded systems and putting them into practical applications.

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
  • Isolation word identification method based on double-layer GMM structure and VTS feature compensation
  • Isolation word identification method based on double-layer GMM structure and VTS feature compensation
  • Isolation word identification method based on double-layer GMM structure and VTS feature compensation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0043] Such as figure 1 As shown, in the model training stage, two GMM models are trained by using the pure speech training data of all isolated words, in which the Gaussian unit mixture number of GMM1 is 10, the Gaussian unit mixture number of GMM2 is 100, and the mixture number of the HMM model is 4 The number of states is 6. The GMM model represents the distribution of characteristic parameters of all isolated words in a pure environment, and the HMM model represents the distribution of characteristic parameters of each isolated word in a pure environment.

[0044]In the recognition stage based on feature compensation, based on the vector Taylor series VTS feature compensation algorithm, according to the GMM1 model obtained in the training stage, the mean value and variance of the noise in the test speech in the test environment are estimated by the maximum likelihood probability criterion ML; then based on the minimum The mean square error estimation criterion MMSE and GM...

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 an isolation word identification method based on a double-layer GMM structure and VTS feature compensation. The method comprises a training stage and an identifying stage. In the training stage, by voice feature extracting under a pure environment, two GMM training models and an HMM training models are obtained. Each GMM model comprises a GMM1 model containing a small number of Gauss mixing units and a GMM2 model containing a large number of Gauss mixing units. During a noise estimation process at a vector Taylor series (VTS) feature compensation stage, the GMM1 model is used for obtaining the mean value and the variance of noise, a GMM2 model is used for obtaining a pure feature parameters by mapping, and matching with the HMM module is carried out to obtain the final identification results. Compared with an isolation word identification algorithm based on a single GMM model and VTS feature compensation, under the situation that the error recognition rate is not changed basically, noise mean value and variance estimating time is shortened by 90%, feature compensation overall time is shortened by 30%-50%, and calculated quantity of the isolation word identification algorithm based on the VTS feature compensation is effectively lowered.

Description

technical field [0001] The invention relates to the field of speech recognition, in particular to an isolated word recognition method based on a double-layer GMM structure and VTS feature compensation. Background technique [0002] In recent years, with the development of speech technology, isolated word recognition technology has been widely used in many fields such as communication, consumer electronics, self-service, office automation, etc. These devices are usually used or installed in noisy public places, which are inevitably subject to Various disturbances, which can seriously affect the performance of the isolated word recognition system. In addition, the long recognition time of the isolated word recognition system has become a disadvantageous factor for transplanting to embedded systems and putting them into practical applications. The compensation module of the local isolated word recognition system of mobile devices and self-service devices has a large amount 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
IPC IPC(8): G10L15/14G10L15/02G10L15/05G10L21/0216
Inventor 周琳李海静吕勇吴镇扬
Owner SOUTHEAST 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