Voiceprint identification method based on Gauss mixing model and system thereof

A Gaussian mixture model and voiceprint recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of random initial parameters of the model and affecting the recognition rate of the system

Inactive Publication Date: 2012-01-18
LIAONING UNIVERSITY OF TECHNOLOGY
View PDF4 Cites 133 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the traditional voiceprint recognition based on GMM, the selection of the initial parameters of the model is relatively random, which seriously affects the recognition rate of the system.

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
  • Voiceprint identification method based on Gauss mixing model and system thereof
  • Voiceprint identification method based on Gauss mixing model and system thereof
  • Voiceprint identification method based on Gauss mixing model and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0094] as attached figure 1 As shown, the voiceprint recognition system based on the Gaussian mixture model is composed as follows:

[0095] Voice signal acquisition module, voice signal preprocessing module, voice signal feature parameter extraction module, voice model training module and voiceprint recognition module.

[0096] Such as Figure 2-Figure 4 As shown, the specific steps of the voiceprint recognition method based on the Gaussian mixture model are as follows:

[0097] 1. Acquisition of voice signals

[0098] The acquisition of voice signal is to convert the original voice analog signal into digital signal, and set the channel number and sampling frequency. The present invention adopts the SHT-8B / PCI type voice card produced by Hangzhou Sanhui Company to collect the voice signal, and the channel number is 2 (The default channel number of the voice card is 2), and the sampling frequency is 8KHz (the default sampling frequency of the voice card). The identified te...

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 provides a voiceprint identification method based on a Gauss mixing model and a system thereof. The method comprises the following steps: voice signal acquisition; voice signal pretreatment; voice signal characteristic parameter extraction: employing a Mel Frequency Cepstrum Coefficient (MFCC), wherein an order number of the MFCC usually is 12-16; model training: employing an EM algorithm to train a Gauss mixing model (GMM) for a voice signal characteristic parameter of a speaker, wherein a k-means algorithm is selected as a parameter initialization method of the model; voiceprint identification: comparing a collected voice signal characteristic parameter to be identified with an established speaker voice model, carrying out determination according to a maximum posterior probability method, and if a corresponding speaker model enables a speaker voice characteristic vector X to be identified to has maximum posterior probability, identifying the speaker. According to the method, the Gauss mixing model based on probability statistics is employed, characteristic distribution of the speaker in characteristic space can be reflected well, a probability density function is common, a parameter in the model is easy to estimate and train, and the method has good identification performance and anti-noise capability.

Description

technical field [0001] The invention belongs to a voice signal processing device, and relates to a Gaussian mixture model-based voiceprint recognition method and system for identifying the speaker's identity by using the speaker's voice signal. Background technique [0002] In recent years, with the wide application of information processing and artificial intelligence technology, and people's urgent requirements for fast and effective identity verification, traditional password authentication has gradually lost its status. In the field of biometrics, speaker-based Voice identification technology has been favored by more and more people. [0003] Due to the physiological differences in the pronunciation organs of each person and the acquired behavioral differences, the pronunciation methods and speaking habits are different, so it is possible to use the speaker's voice to identify the identity. In addition to the advantages of no forgetting, no need to remember, and conveni...

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): G10L15/02G10L15/06G10L17/02
Inventor 霍春宝张健赵立辉刘春玲张彩娟
Owner LIAONING UNIVERSITY OF TECHNOLOGY
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