Multi-Level Liveness Verification for Face-Voice Biometric Authentication

Girija Chetty; Michael Wagner

doi:10.1109/BCC.2006.4341615

Multi-Level Liveness Verification for Face-Voice Biometric Authentication

Girija Chetty, Michael Wagner

Information Systems

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

54 Citations (Scopus)

187 Downloads (Pure)

Abstract

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 language	English
Title of host publication	2006 Biometrics Symposium Special Session on Research at the Biometric Consortium Conference
Editors	Larue Williams
Place of Publication	USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1-6
Number of pages	6
ISBN (Print)	9781424404865
DOIs	https://doi.org/10.1109/BCC.2006.4341615
Publication status	Published - 2006
Event	2006 Biometrics Symposium - Baltimore, United States Duration: 19 Sept 2006 → 21 Sept 2006

Conference

Conference	2006 Biometrics Symposium
Country/Territory	United States
City	Baltimore
Period	19/09/06 → 21/09/06

Access to Document

10.1109/BCC.2006.4341615

PaperFinal published version, 5.54 MB

Cite this

@inproceedings{ebb6df849f174c33bc9df41b799a296d,

title = "Multi-Level Liveness Verification for Face-Voice Biometric Authentication",

abstract = "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",

author = "Girija Chetty and Michael Wagner",

year = "2006",

doi = "10.1109/BCC.2006.4341615",

language = "English",

isbn = "9781424404865",

pages = "1--6",

editor = "Larue Williams",

booktitle = "2006 Biometrics Symposium Special Session on Research at the Biometric Consortium Conference",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2006 Biometrics Symposium ; Conference date: 19-09-2006 Through 21-09-2006",

}

Chetty, G & Wagner, M 2006, Multi-Level Liveness Verification for Face-Voice Biometric Authentication. in L Williams (ed.), 2006 Biometrics Symposium Special Session on Research at the Biometric Consortium Conference . IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 1-6, 2006 Biometrics Symposium, Baltimore, United States, 19/09/06. https://doi.org/10.1109/BCC.2006.4341615

Multi-Level Liveness Verification for Face-Voice Biometric Authentication. / Chetty, Girija; Wagner, Michael.
2006 Biometrics Symposium Special Session on Research at the Biometric Consortium Conference . ed. / Larue Williams. USA: IEEE, Institute of Electrical and Electronics Engineers, 2006. p. 1-6.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - Multi-Level Liveness Verification for Face-Voice Biometric Authentication

AU - Chetty, Girija

AU - Wagner, Michael

PY - 2006

Y1 - 2006

N2 - 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

AB - 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

U2 - 10.1109/BCC.2006.4341615

DO - 10.1109/BCC.2006.4341615

M3 - Conference contribution

SN - 9781424404865

SP - 1

EP - 6

BT - 2006 Biometrics Symposium Special Session on Research at the Biometric Consortium Conference

A2 - Williams, Larue

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

T2 - 2006 Biometrics Symposium

Y2 - 19 September 2006 through 21 September 2006

ER -

Multi-Level Liveness Verification for Face-Voice Biometric Authentication

Abstract

Conference

Access to Document

Fingerprint

Cite this