Multi-Level Liveness Verification for Face-Voice Biometric Authentication

Girija Chetty, Michael Wagner

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

54 Citations (Scopus)
176 Downloads (Pure)


In this paper we present the details of the multilevel liveness verification (MLLV) framework proposed for realizing a secure face-voice biometric authentication system that can thwart different types of audio and video replay attacks. The proposed MLLV framework based on novel feature extraction and multimodal fusion approaches, uncovers the static and dynamic relationship between voice and face information from speaking faces, and allows multiple levels of security. Experiments with three different speaking corpora VidTIMIT, UCBN and AVOZES shows a significant improvement in system performance in terms of DET curves and equal error rates (EER) for different types of replay and synthesis attacks
Original languageEnglish
Title of host publication2006 Biometrics Symposium Special Session on Research at the Biometric Consortium Conference
EditorsLarue Williams
Place of PublicationUSA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Print)9781424404865
Publication statusPublished - 2006
Event2006 Biometrics Symposium - Baltimore, United States
Duration: 19 Sept 200621 Sept 2006


Conference2006 Biometrics Symposium
Country/TerritoryUnited States


Dive into the research topics of 'Multi-Level Liveness Verification for Face-Voice Biometric Authentication'. Together they form a unique fingerprint.

Cite this