Long window scaling factor-based playback voice attack detection algorithm

A scaling factor and attack detection technology, applied in speech analysis, instruments, etc., to achieve the effect of improving security issues, high detection accuracy, and improving attack capabilities

Active Publication Date: 2016-08-31
NINGBO UNIV
View PDF4 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] From the above analysis, it can be seen that the existing algorithms mainly focus on the acoustic properties and channel characteristics of the speech signal, and have not set foot in the characteristics of the coding parameters. However, according to the physical process of the playback speech and the original speech generation, the playback speech has undergone more than one surreptitious recording. Equipment and playback equipment, this process will inevitably involve quantization in codec, due to the existence of quantization errors, speech from different sources will have differences in some encoding parameters

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
  • Long window scaling factor-based playback voice attack detection algorithm
  • Long window scaling factor-based playback voice attack detection algorithm
  • Long window scaling factor-based playback voice attack detection algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The embodiments of the present invention will be described in detail below in conjunction with the above-mentioned drawings.

[0028] A replay voice attack detection algorithm based on the long window scale factor. It is a detection algorithm developed to prevent the legitimate user's rights and interests by using the replay voice to enter the speaker recognition system by using the replay voice. After the detection algorithm module is loaded into the GMM-UBM system, it improves the ability to resist playback voice attacks, reduces the equal error probability of the recognition system by 32%, and greatly improves the security of the recognition system.

[0029] The detection algorithm involves the basic concepts of the GMM-UBM identification system and the long window scale factor, specifically:

[0030] GMM-UBM identification system

[0031] GMM-UBM (Gaussian Mixture Model - Universal Background Model) is called the Gaussian mixture model based on the universal backgr...

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 long window scaling factor-based playback voice attack detection algorithm which is developed for solving a problem that rights and interests of a legitimate are damaged when conventional attackers use playback voice to enter a speaker identification system. The detection algorithm can be used for effectively identifying playback voice from different sources and is high in detection accuracy; after a module of the detection algorithm is loaded to a GMM-UBM system, playback voice attack resistant capability is improved, error probability of the identification system and the like is lowered by 32%, and a safety problem of the identification system is greatly alleviated.

Description

technical field [0001] The invention relates to a playback voice attack detection algorithm, in particular to a playback voice attack detection algorithm based on a long window scale factor. Background technique [0002] In the field of biometric identification technology, speaker recognition technology has been gradually applied in fields such as finance, social security, and ordinary life due to its advantages such as easy acquisition, low-cost voice pickup equipment, and support for off-site identity verification. However, with the popularization of portable and high-fidelity recording equipment, it is very easy for an attacker to secretly record a legitimate user's password when requesting to enter the identification system. If an attacker uses a high-fidelity audio system to play back secretly recorded voices and successfully attacks the authentication system, the safety and interests of users will be threatened, and property loss or information leakage may be inevitabl...

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): G10L25/03G10L25/78
CPCG10L25/03G10L25/78
Inventor 王让定陈亚楠严迪群金超陶表犁张立
Owner NINGBO 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