Supercharge Your Innovation With Domain-Expert AI Agents!

Method and device for identifying camouflaged voices

A recognition method and sound technology, applied in speech analysis, instruments, etc., can solve the problems of recognition failure, high missed detection rate and false alarm rate, and achieve the effect of low missed detection and false alarm rate and improved recognition performance

Inactive Publication Date: 2016-08-24
SUN YAT SEN UNIV +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The experimental results show that after the voice has undergone a large conversion, the conventional speaker recognition scheme will cause a high or extremely high missed detection rate and false alarm rate, and the recognition is completely invalid.

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 and device for identifying camouflaged voices
  • Method and device for identifying camouflaged voices
  • Method and device for identifying camouflaged voices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0082] Such as Figure 3-6 As shown, the present invention discloses that in the training phase, the EM (Expectation Maximum) algorithm is used to calculate the UBM (uniform background model) λ from the background speech database bkg ; In the training phase, extract the test speech S of speaker j j The MFCC coefficient and fundamental frequency of , using the MAP ((Maximum A posteriori, maximum a posteriori probability) algorithm to calculate the speaker j's GMM (Gaussian Mixture Model) model λ j , to calculate the mean value of the fundamental frequency f j . Build a model V of speaker j j =(λ j , f j ), and stored in the model database. The threshold θ is obtained during the training phase. In the test phase, the voice Y is the converted voice, and its fundamental frequency average value f is extracted Y . use f Y / f j Calculate the conversion coefficient; use the improved MFCC extraction algorithm to calculate the original MFCC coefficient X before Y conversion. ...

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 method and device for recognizing disguised sounds. The method is characterized in that the voice transformation coefficient is estimated through fundamental frequency characteristics of voices, and an Mel frequency cepstrum coefficient extraction algorithm is improved, namely the estimated coefficient is integrated into the Mel frequency cepstrum coefficient extraction algorithm through linear interpolation extension so that the Mel frequency cepstrum coefficient of the before-transformation voices can be approximately calculated. Finally, the method is integrated into a GMM-UBM recognizing frame to calculate the similarity between the voices, and meanwhile the transformed voices can be restored into the original voices through the estimated transformation coefficient. According to the method and device, a great improvement is achieved on the recognizing performance compared with a conventional recognizing evidence-obtaining method, and detection missing and the false alarm are both lower than the detection missing and the false alarm of a conventional scheme.

Description

technical field [0001] The present invention relates to the field of multimedia information security, and more particularly, relates to a method and device for identifying fake voices. Background technique [0002] Voice Transformation is one of the most commonly used speech processing methods. Its function is to change one sound into another sound that sounds natural but completely different. Voice conversion is commonly used in music production or to protect the safety and privacy of the speaker, but it can also be used by criminals to mask voices so that they cannot be identified. Therefore, speaker identification after speech conversion has important application value. [0003] General steps for voice conversion: [0004] 1) Framing and windowing the signal x(n): [0005] F ( k ) = Σ n = 0 N ...

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 Patents(China)
IPC IPC(8): G10L17/04
Inventor 王泳黄继武
Owner SUN YAT SEN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com