Liveness Detection Using Cross-Modal Correlations in Face-Voice Person Authentication

Girija Chetty, Michael Wagner

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

18 Citations (Scopus)

Abstract

In this paper we show the potential of two new features as powerful anti-spoofing measures for face-voice person authentication systems. The features based on latent semantic analysis (LSA) and canonical correlation analysis (CCA), enhance the performance of the authentication system in terms of better anti-imposture abilities and guard against video replay attacks, which is a challenging type of spoof attack. Experiments conducted on 2 speaking-face databases, VidTIMIT and UCBN, show around 42% improvement in error rate with CCA features and 61% improvement with LSA features over feature-level fusion of face-voice feature vectors.
Original languageEnglish
Title of host publication6th Interspeech 2005 and 9th European Conference on Speech Communication and Technology (EUROSPEECH)
EditorsTrancoso Flurui
Place of PublicationGeneva
PublisherInternational Speech Communication Association
Pages2181-2184
Number of pages4
ISBN (Print)9781604234480
Publication statusPublished - 2005
Event6th Interspeech 2005 and 9th European Conference on Speech Communication and Technology (EUROSPEECH 2005) - Lisboa, Lisboa, Portugal
Duration: 4 Sept 20058 Sept 2005

Conference

Conference6th Interspeech 2005 and 9th European Conference on Speech Communication and Technology (EUROSPEECH 2005)
Country/TerritoryPortugal
CityLisboa
Period4/09/058/09/05

Fingerprint

Dive into the research topics of 'Liveness Detection Using Cross-Modal Correlations in Face-Voice Person Authentication'. Together they form a unique fingerprint.

Cite this