Audio-Visual Identity Verification: an Introductory Overview - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2007

Audio-Visual Identity Verification: an Introductory Overview

Résumé

Verification of identity is commonly achieved by looking at the face of a person and listening to his (her) speech. Automatic means of achieving this verification has been studied for several decades. Indeed, a talking face offers many features to achieve a robust verification of identity. The current deployment of videophones drives new opportunities for a secured access to remote servers (banking, certification, call centers, etc.). The synchrony of the speech signal and lip movements is a necessary condition to check that the observed talking face has not been manipulated and/or synthesized. This overview addresses face, speaker and talking face verification, as well as face and voice transformation techniques. It is demonstrated that a dedicated impostor needs limited information from a client to fool state of the art audio-visual identity verification systems.

Dates et versions

hal-01987800 , version 1 (21-01-2019)

Identifiants

Citer

Guido Aversano, Gérard Chollet, Bouchra Abboud, Hervé Bredin. Audio-Visual Identity Verification: an Introductory Overview. Yannis Stylianou. Progress in Nonlinear Speech Processing, 4391, Springer Verlag, pp.118-134, 2007, 978-3-540-71503-0. ⟨10.1007/978-3-540-71505-4_8⟩. ⟨hal-01987800⟩
52 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More