Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/98757
Title: | Vulnerability of speaker verification systems against voice conversion spoofing attacks : the case of telephone speech | Authors: | Kinnunen, Tomi Wu, Zhizheng Lee, Kong Aik Sedlak, Filip Chng, Eng Siong Li, Haizhou |
Keywords: | DRNTU::Engineering::Computer science and engineering | Issue Date: | 2012 | Conference: | IEEE International Conference on Acoustics, Speech and Signal Processing (2012 : Kyoto, Japan) | Abstract: | Voice conversion - the methodology of automatically converting one's utterances to sound as if spoken by another speaker - presents a threat for applications relying on speaker verification. We study vulnerability of text-independent speaker verification systems against voice conversion attacks using telephone speech. We implemented a voice conversion systems with two types of features and nonparallel frame alignment methods and five speaker verification systems ranging from simple Gaussian mixture models (GMMs) to state-of-the-art joint factor analysis (JFA) recognizer. Experiments on a subset of NIST 2006 SRE corpus indicate that the JFA method is most resilient against conversion attacks. But even it experiences more than 5-fold increase in the false acceptance rate from 3.24 % to 17.33 %. | URI: | https://hdl.handle.net/10356/98757 http://hdl.handle.net/10220/13414 |
DOI: | 10.1109/ICASSP.2012.6288895 | Schools: | School of Computer Engineering | Rights: | © 2012 IEEE | Fulltext Permission: | none | Fulltext Availability: | No Fulltext |
Appears in Collections: | SCSE Conference Papers |
SCOPUSTM
Citations
5
162
Updated on Mar 12, 2024
Page view(s) 20
679
Updated on Mar 26, 2024
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.