Sparse representation based short-voice speaker recognition method

A technology of speaker recognition and sparse representation, which is applied in the field of short speech speaker recognition based on sparse representation, and can solve the problems that the speaker model cannot effectively improve the recognition accuracy and semantic information mismatch.

Inactive Publication Date: 2013-10-09
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 53 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the prior art, the technical problem mainly solved by the present invention is to provide a short speech speaker recognition method based on sparse representation, which can not effectively improve the existing technology when the semantic information does not match and the speaker model does not match. The problem of recognition accuracy

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
  • Sparse representation based short-voice speaker recognition method
  • Sparse representation based short-voice speaker recognition method
  • Sparse representation based short-voice speaker recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0052] Such as figure 1 As shown, a short speech speaker recognition method based on sparse representation includes the following steps:

[0053] Step 1: Pre-processing all voice samples, mainly including pre-emphasis, frame windowing, endpoint detection, and then extract MFCC and its first-order difference coefficients as features;

[0054] Step 2: Train the Gaussian background model from the background speech database, and extract the Gaussian supervector as the secondary feature;

[0055] Step 3: Arrange the Gaussian supervectors of the training speech samples together to form a dictionary;

[0056] Step 4: Use the sparse solution algorithm to solve the representation coefficient, reconstruct the signal, and determine the recognition result according to the minimized residual.

[0057] In such figure 2 As shown, the first step includes steps S11, S12, S13, and S14, which are specifically described as follows:

[0058] S11: Pre-emphasis, high-frequency speech signal is an indispensab...

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 sparse representation based short-voice speaker recognition method, which belongs to the technical field of voice signal processing and pattern recognition, and aims to solve the problem that the existing method is low in recognition rate under limited voice data conditions. The method mainly comprises the following steps: (1) pretreating all voice samples, and then extracting Mel-frequency cepstral coefficients and first-order difference coefficients thereof as characteristic; (2) training a gaussian background model by a background voice library, and extracting gaussian supervectors as secondary characteristics; (3) arranging the gaussian supervectors for training voice samples together so as to form a dictionary; and (4) solving an expression coefficient by using a sparse solving algorithm, reconstructing signals, and determining a recognition result according to a minimized residual error. According to the invention, the gaussian supervectors obtained through self-adaption can greatly relieve the problem that the personality characteristics of a speaker are expressed insufficiently due to limited voice data; through carrying out classification by using sparsely represented reconstructed residual errors, a speaker model mismatch problem caused by mismatched semantic information can be handled.

Description

Technical field [0001] The invention belongs to the technical field of speech signal processing and pattern recognition, especially speaker recognition technology under short speech conditions, and specifically relates to a short speech speaker recognition method based on sparse representation. Background technique [0002] Speaker recognition technology refers to the use of speaker's voice characteristics to identify their identities. It belongs to the category of biometric authentication technology and is widely used in judicial authentication, Internet security, and military defense. There are still many problems in the practical process of speaker recognition technology. Among them, the problem of training recognition under short speech conditions has attracted widespread attention. [0003] At present, the Gaussian Mixture Model-Universal Background Model (GMM-UBM) is widely used at home and abroad for short speech problems. Initially, likelihood ratio scores or template match...

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): G10L17/00G10L17/04
Inventor 程建黎兰苏靖峰周圣云李鸿升
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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