Dominique Genoud

Learn More
This paper describes a multimodal approach for speaker verification. The system consists of two classifiers, one using visual features, the other using acoustic features. A lip tracker is used to extract visual information from the speaking face which provides shape and intensity features. We describe an approach for normalizing and mapping different(More)
R ´ ESUMÉ Cet article présente une description de la base de données POLYCOST qui est dédiée aux applications de reconnaissance du locuteurà travers les lignes téléphoniques. Les car-actéristiques de la base de données sont : large corpusà con-tenu varié (> 100 locuteurs), anglais parlé par desétrangers, chiffres lus et parole libre, enregistrementà travers(More)
The aim of this paper is to describe how the combination of speaker verication algorithms with a priori decision thresholds can improve the overall robustness of a real application. The evaluation is performed in the context of a eld application where each client i s v eried from a 7 digit pin code. This paper demonstrate that it is possible to increase the(More)
The issue of a priori threshold setting in speaker veri-cation is a key problem for eld applications. In the context of the CAVE project, we compared several methods for estimating speaker-independent and speaker-dependent decision thresholds. Relevant parameters are estimated from development data only, i.e. without resorting to additional client data. The(More)
In speaker verification, two independent stochastic models, i.e. a client model and a non-client (world) model, are generally used to verify the claimed identity using a likelihood ratio score. This paper investigates a variant of this approach based on a common hidden process for both models. In this framework, both models share the same topology, which is(More)
R ESUM E Cet article pr esente un panorama des activit es de recherche men ees dans le cadre du projet europ een LE-Telematics CAVE, sur la v eriication du locuteur a travers le r eseau t el ephonique. Nous pr esentons tout d'abord les principes des algorithmes sur lesquels repose notre syst eme de v eri-cation. Nous d ecrivons ensuite le protocole et la(More)
Cet article pr esente une m ethode d'ajustement des seuils de v eriication du locuteur bas ee sur un mod ele Gaussien des distributions du logarithme du rapport de vraisemblance. L'article expose les hypoth eses sous lesquelles ce mod ele est valide, indique plusieurs m ethodes d'ajustement des seuils, et en illustre les apports et les limites par des exp(More)
L L k t t t kf j i a k i a i a e t A t h))((2 0) () (ˆ i a t ABSTRACT Recently, some large-scale text dependent speaker verification systems have been tested. They show that less than 1% Equal Error Rate can be obtained on a test set score distribution. So far, the majority of impostor tests are performed using speakers who don't really try to fool the(More)