"Liveness" Verification in Audio-Video Authentication

Girija Chetty, Michael Wagner

Research output: A Conference proceeding or a Chapter in BookConference contribution

24 Citations (Scopus)
15 Downloads (Pure)

Abstract

This paper proposes to use combined acoustic and visual feature vectors to distinguish live synchronous audio-video recordings from replay attacks that use audio with a still photo. Equal error rates below 2 % are achieved using a multi-dimensional eigenlip representation and EERs of 7% are achieved with a one-dimensional lip-opening ratio.
Original languageEnglish
Title of host publicationProceedings Interspeech 2004
EditorsSoon Hyob Kim, Dae Hee Youn
Place of PublicationJeju, Korea
PublisherInterspeech 2004
Pages2509-2512
Number of pages4
ISBN (Print)1225-441X
Publication statusPublished - 2004
EventINTERSPEECH 2004 - ICSLP 8th International Conference on Spoken Language Processing - Jeju, Korea, Republic of
Duration: 3 Oct 20047 Oct 2004

Conference

ConferenceINTERSPEECH 2004 - ICSLP 8th International Conference on Spoken Language Processing
CountryKorea, Republic of
CityJeju
Period3/10/047/10/04

Fingerprint Dive into the research topics of '"Liveness" Verification in Audio-Video Authentication'. Together they form a unique fingerprint.

  • Cite this

    Chetty, G., & Wagner, M. (2004). "Liveness" Verification in Audio-Video Authentication. In S. H. Kim, & D. H. Youn (Eds.), Proceedings Interspeech 2004 (pp. 2509-2512). Interspeech 2004. https://www.isca-speech.org/archive/archive_papers/interspeech_2004/i04_2509.pdf