Method for recognizing speaker based on conversion of neutral and affection sound-groove model

A speaker recognition and model conversion technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems affecting system recognition performance and achieve the effect of improving recognition rate

Inactive Publication Date: 2008-07-23
ZHEJIANG UNIV
View PDF0 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Traditional speaker recognition methods require users to provide neutral speech for user model training and user testing, but in da

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
  • Method for recognizing speaker based on conversion of neutral and affection sound-groove model
  • Method for recognizing speaker based on conversion of neutral and affection sound-groove model
  • Method for recognizing speaker based on conversion of neutral and affection sound-groove model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] The present invention will be further introduced below in conjunction with accompanying drawing and embodiment: the method of the present invention is divided into three steps altogether.

[0012] The first step feature extraction

[0013] I. Audio preprocessing

[0014] Audio preprocessing is divided into three parts: sampling quantization, zero drift removal, pre-emphasis and windowing.

[0015] A), sampling quantization

[0016] Filter the audio signal with a sharp cut-off filter so that its Nyquist frequency FN is 4KHZ;

[0017] Set the audio sampling rate F=2FN; the audio signal sa(t) is sampled periodically to obtain the amplitude sequence of the digital audio signal s ( n ) = sa ( n F ) ;

[0018] Quantize and code s(n) with pulse code modulation (PCM) to obtain the quantized representation...

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 speaker identification method based on neutralization and sound-groove model conversion, the steps comprises (1) extracting voice feature, firstly conducting voice frequency pre-treating which is divided into three parts of sample-taking quantification, zero drift elimination, then extracting reverse spectrum signature MFCC, (2) building emotion model library, conducting Gaussian compound model training, training neutral model according to the neutral voice training of the users, conducting neutralization-emotion model conversion and obtaining emotion voice model by algorithm approach of neutralization-emotion voice conversion and (3) scoring for the voice test to identify the speakers. The invention has the advantages that the technique uses the algorithm approach of neutralization-emotion model conversion to increase the identification rate of the emotive speaker identifying. The technique trains out emotion voice model of the users according to the neutralization voice model of the users and increases the identification rate of the system.

Description

technical field [0001] The invention relates to biological feature recognition technology, and mainly relates to a speaker recognition method based on conversion of neutral and emotional voiceprint models. Background technique [0002] Biometric authentication technology uses people's own physical characteristics as the basis for identity authentication, which is fundamentally different from traditional authentication technologies based on "what you have" or "what you know", and truly uses people themselves as the basis for identity authentication , who truly represent themselves. Among them, the technology of identity authentication based on human voice is called speaker recognition technology. [0003] Speaker recognition is divided into two steps: user model training and user voice testing. During the training process, the user is required to provide a user model for voice training and user identity matching. During the test, the user is required to provide voice for i...

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): G10L17/00G10L15/02G10L15/06G10L15/08G10L17/02G10L17/04G10L25/24
Inventor 吴朝晖杨莹春单振宇
Owner ZHEJIANG 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