Speaker Recognition Anti-spoofing

Nicholas Evans, Tomi Kinnunen, Junichi Yamagishi, Zhizheng Wu, Federico Alegre, Phillip De Leon

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Progress in the development of spoofing countermeasures for automatic speaker recognition is less advanced than equivalent work related to other biometric modalities. This chapter outlines the potential for even state-of-the-art automatic speaker recognition systems to be spoofed. While the use of a multitude of different datasets, protocols and metrics complicates the meaningful comparison of different vulnerabilities, we review previous work related to impersonation, replay, speech synthesis and voice conversion spoofing attacks. The article also presents an analysis of the early work to develop spoofing countermeasures. The literature shows that there is significant potential for automatic speaker verification systems to be spoofed, that significant further work is required to develop generalised countermeasures, that there is a need for standard datasets, evaluation protocols and metrics and that greater emphasis should be placed on text-dependent scenarios.
Original languageEnglish
Title of host publicationHandbook of Biometric Anti-Spoofing
EditorsSébastien Marcel, Mark S. Nixon, Stan Z. Li
PublisherSpringer London
Pages125-146
Number of pages22
ISBN (Electronic)978-1-4471-6524-8
ISBN (Print)978-1-4471-6523-1
DOIs
Publication statusPublished - 2014

Publication series

NameAdvances in Computer Vision and Pattern Recognition
PublisherSpringer London
ISSN (Print)2191-6586

Fingerprint Dive into the research topics of 'Speaker Recognition Anti-spoofing'. Together they form a unique fingerprint.

Cite this