Speaker recognition self-adaption method in complex environment based on GMM model

A technology for speaker recognition and complex environments, which is applied in the field of self-adaptive speaker recognition in complex environments based on the GMM model, can solve problems such as surrounding noise interference, achieve the effects of improving accuracy, avoiding the reduction of recognition rate, and realizing self-adaptation

Active Publication Date: 2020-08-04
WUHAN UNIV
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] At the same time, the extracted voice will also be disturbed by surrounding noise, etc. How to ef

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
  • Speaker recognition self-adaption method in complex environment based on GMM model
  • Speaker recognition self-adaption method in complex environment based on GMM model
  • Speaker recognition self-adaption method in complex environment based on GMM model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0062] In order to overcome the shortcomings of lower speaker recognition accuracy due to illness or complex environment, this embodiment proposes a new method of combining feature parameters, which can combine and analyze different features, and effectively compensate for the voice changes caused by illness or noise. errors and improve recognition accuracy.

[0063] An adaptive method for speaker recognition in a complex environment based on the GMM model, including: the construction stage of the speaker recognition model based on the GMM, that is, after preprocessing the speech signal such as low-pass filtering, pre-emphasis, windowing, and framing , filter and denoise through the Gammatone filter, and extract the GMFCC combination feature parameters. In the speaker recognition and self-adaptation stage, the speaker recognition is completed by extra...

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 signal processing technology, and in particular, relates to a speaker recognition self-adaption method in a complex environment based on a GMM model. The method comprises aGMM-based speaker recognition model construction stage, that is to say, after low-pass filtering, pre-emphasis, windowing, framing and other preprocessing are carried out on a voice signal, filteringand denoising are carried out through a Gammatone filter, and GMFCC combined characteristic parameters are extracted. The method further comprises a speaker recognition and self-adaptation stage, thatis to say, speaker recognition is completed by extracting speech feature parameters of a speaker to be recognized and conducting self-adaptation adjustment on the original model. According to the method, the defect that the speaker recognition accuracy is reduced due to illness or complex environment is overcome, a new feature parameter combination method is provided, different features can be analyzed in a combined mode, errors caused by voice changes due to different conditions of speakers are effectively compensated, and thus the recognition accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of signal processing, and in particular relates to an adaptive method for speaker recognition in a complex environment based on a GMM model. Background technique [0002] Speaker recognition is a method of feature extraction through the collected speaker's voice signal, analysis and processing, and then identification or confirmation of the speaker. With the rapid development of today's Internet and information technology, more and more related fields will use speaker recognition technology. As a cutting-edge technology, speaker recognition is widely used in smart home, judicial criminal investigation, identity verification and other fields. [0003] With the deepening of speaker recognition research, its key technologies mainly revolve around issues such as noise elimination, feature extraction and pattern matching. [0004] How to extract the speaker's personality from the speaker's voice signal is the k...

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): G10L25/24G10L25/51
CPCG10L25/24G10L25/51
Inventor 郭雨欣宋雨佳
Owner WUHAN 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