Making talking-face authentication robust to deliberate imposture

被引：12

作者：

Bredin, Hervie ^{[1
]}

Chollet, Gerard ^{[1
]}

机构：

[1] CNRS LTCI, Dept TSI, GET ENST, Paris, France

来源：

2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12 | 2008年

关键词：

robustness; speaker recognition; face recognition;

D O I：

10.1109/ICASSP.2008.4517954

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

We expose the limitations of existing frameworks designed for the evaluation of audiovisual biometric authentication algorithms. The weakness of a classical audiovisual authentication system is uncovered when confronted to realistic deliberate impostors. A client-dependent audiovisual synchrony measure is used in order to deal with deliberate impostors and three new fusion strategies and their performance against random and deliberate impostors are studied.

引用

页码：1693 / 1696

页数：4

共 11 条

[1] Audio-visual biometrics [J].

Aleksic, Petar S. ;

Katsaggelos, Aggelos K. .

PROCEEDINGS OF THE IEEE, 2006, 94 (11) :2025-2044

[2]

[Anonymous], 2006, Handbook of multibiometrics

[3]

BENGIO S, 2004, ODYSSEY 2004 SPEAK L, P237

[4]

BREDIN H, 2007, 32 IEEE INT C AC SPE

[5]

CHETTY G, 2004, 10 AUSTR INT C SPEEC, P358

[6]

ENRIQUE BB, 2003, LECT NOTES COMPUTER, V2688, P625

[7] A generative framework for real time object detection and classification [J].

Fasel, I ;

Fortenberry, B ;

Movellan, J .

COMPUTER VISION AND IMAGE UNDERSTANDING, 2005, 98 (01) :182-210

[8]

Jee H.K., 2006, International Journal of Biomedical Sciences, V1, P235

[9] Speaker verification using adapted Gaussian mixture models [J].

Reynolds, DA ;

Quatieri, TF ;

Dunn, RB .

DIGITAL SIGNAL PROCESSING, 2000, 10 (1-3) :19-41

[10]

SANTANA MC, 2005, 2 IB C PATT REC IM

← 1 2 →