Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Voice spoofing attack detection method based on voice signal spectrum characteristics and deep learning

A technology of spectrum characteristics and voice signals, applied in the field of voice authentication technology and security, can solve the problems of low detection accuracy, poor user experience, difficult to apply, etc., and achieve the effect of solving network degradation, low cost, and improving sensitivity

Active Publication Date: 2021-01-08
ZHEJIANG UNIV
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this type of detection method usually has low detection accuracy and is difficult to apply after the attack method and equipment are upgraded.
In addition, there is a defense method for liveness detection by wearing additional equipment on the user. This method requires high cost and poor user experience due to the need for additional equipment.

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
  • Voice spoofing attack detection method based on voice signal spectrum characteristics and deep learning
  • Voice spoofing attack detection method based on voice signal spectrum characteristics and deep learning
  • Voice spoofing attack detection method based on voice signal spectrum characteristics and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043]The present invention will be further described below in conjunction with the drawings.

[0044]The complete implementation of the method according to the present invention and its implementation are as follows:

[0045]1) Signal processing:

[0046]Such asfigure 1 As shown, the original voice signal Voicein Follow the following two steps to obtain the cumulative power spectrum Spow :

[0047]The first step adopts short-time Fourier transform. The process of short-time Fourier transform is as follows: First, use a periodic Hamming window with a length of 1024 (representing 1024 data points) and an overlap length of 768 to compare the original voice signal Voicein Perform windowing processing to convert the original voice signal Voicein Divide into multiple data frames with a length of 1024, and then perform fast Fourier transform on each data frame, and the number of Fourier transform points nfft is 4096;

[0048]The second step is to accumulate the results of the fast Fourier transform of e...

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 voice spoofing attack detection method based on voice signal spectrum characteristics and deep learning. After a microphone of the electronic equipment receives a voice signal, signal processing work is carried out on voice, then specific features are extracted, finally, the marked features are input into a classifier of a deep convolutional neural network SE-ResNet to betrained, and the trained classifier is adopted to carry out voice living body detection on the voice signal to be detected. and a result of whether the voice is sent by the human voice or the voice attack is replayed is output. According to the invention, the voice spoofing attack represented by the replay attack for the speaker recognition system can be accurately and effectively detected.

Description

Technical field[0001]The invention belongs to the field of voice authentication technology and safety technology, and specifically relates to a voice-producing body authentication technology based on the frequency spectrum characteristics of a voice signal, and a software processing method capable of detecting voice spoofing attacks against a speaker recognition system.Background technique[0002]The speaker authentication system is a security authentication system that authenticates the speaker's identity by extracting the speaker's voice characteristics and performing feature pattern learning and matching. Due to its low hardware requirements (only a microphone), low cost, simple and convenient user operation, and long-distance non-contact authentication, it has gradually become a mainstream user authentication and access control method. It has been widely used in devices such as speakers and smart homes.[0003]However, existing voice authentication systems are generally vulnerable t...

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): G10L17/00G10L17/02G10L17/04G10L17/06H04L29/06
CPCG10L17/02G10L17/06G10L17/04H04L63/1416H04L63/1466
Inventor 徐文渊冀晓宇王炎周瑜薛晖金子植石卓杨闫琛
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com