Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems

Fuming Fang, Junichi Yamagishi, Isao Echizen, Md Sahidullah, Tomi Kinnunen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Automatic speaker verification (ASV) systems use a playback detector to filter out playback attacks and ensure verification reliability. Since current playback detection models are almost always trained using genuine and playedback speech, it may be possible to degrade their performance by transforming the acoustic characteristics of the played-back speech close to that of the genuine speech. One way to do this is to enhance speech “stolen” from the target speaker before playback. We tested the effectiveness of a playback attack using this method by using the speech enhancement generative adversarial network to transform acoustic characteristics. Experimental results showed that use of this “enhanced stolen speech” method significantly increases the equal error rates for the baseline used in the ASVspoof 2017 challenge and for a light convolutional neural network-based method. The results also showed that its use degrades the performance of a Gaussian mixture modeluniversal background model-based ASV system. This type of attack is thus an urgent problem needing to be solved.
Original languageEnglish
Title of host publicationIEEE International Workshop on Information Forensics and Security (WIFS) 2018
Place of PublicationHong Kong
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages9
ISBN (Electronic)978-1-5386-6536-7
ISBN (Print)978-1-5386-6537-4
DOIs
Publication statusPublished - 31 Jan 2019
EventIEEE International Workshop on Information Forensics and Security 2018 - , Hong Kong
Duration: 11 Dec 201813 Dec 2018
http://wifs2018.comp.polyu.edu.hk/index.php

Publication series

Name
PublisherIEEE
ISSN (Print)2157-4766
ISSN (Electronic)2157-4774

Conference

ConferenceIEEE International Workshop on Information Forensics and Security 2018
Abbreviated titleWIFS 2018
Country/TerritoryHong Kong
Period11/12/1813/12/18
Internet address

Fingerprint

Dive into the research topics of 'Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems'. Together they form a unique fingerprint.

Cite this