Vulnerability of speaker verification systems against voice conversion spoofing attacks: The case of telephone speech

Citations Over TimeTop 1% of 2012 papers

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 %.

Related Papers

• → SASV 2022: The First Spoofing-Aware Speaker Verification Challenge(2022)43 cited
• → On the potential of jointly-optimised solutions to spoofing attack detection and automatic speaker verification(2022)5 cited
• → SASV Challenge 2022: A Spoofing Aware Speaker Verification Challenge Evaluation Plan(2022)16 cited
• → SASV 2022: The First Spoofing-Aware Speaker Verification Challenge(2022)4 cited
• → Multi-task Learning Based Spoofing-Robust Automatic Speaker Verification System(2020)