J
Jamal Kharroubi
Publications - 6
Citations - 86
Jamal Kharroubi is an academic researcher. The author has contributed to research in topics: Speaker recognition & NIST. The author has an hindex of 6, co-authored 6 publications receiving 85 citations.
Papers
More filters
Proceedings Article
Combining GMM's with Suport Vector Machines for Text-independent Speaker Verification
TL;DR: This paper addresses the issue of using the Support Vector Learning technique in combination with the currently well performing GMM models, in order to improve speaker verification results.
The ELISA Systems for the NIST"99 Evaluation in Speaker Detection and Tracking
B. Nedic,Frédéric Bimbot,Raphaël Blouet,Jean-François Bonastre,Gilles Caloz,Jan Cernocky,Gérard Chollet,G. Durou,Corinne Fredouille,Dominique Genoud,Guillaume Gravier,Jean Hennebert,Jamal Kharroubi,Ivan Magrin-Chagnolleau,Teva Merlin,Chafic Mokbel,D. Petrovska-Delacretaz,Stéphane Pigeon,Mouhamadou Seck,Patrick Verlinde,M. Zouhal +20 more
TL;DR: This article presents the text-independent speaker detection and tracking systems developed by the members of the {ELISA} Consortium for the {NIST'99} speaker recognition evaluation campaign.
Proceedings Article
An overview of the Picasso project research activities in speaker verification for telephone applications
Frédéric Bimbot,Mats Blomberg,Louis Boves,Gérard Chollet,Cédric Jaboulet,Bruno Jacob,Jamal Kharroubi,Johan Koolwaaij,Johan Lindberg,Johnny Mariéthoz,Chafic Mokbel,Houda Mokbel +11 more
TL;DR: The general formalism used by the European PICASSO project on speaker verification for telephone applications is described, and the Picassoft research platform is described.
Journal ArticleDOI
On the Use of Prior Knowledge in Normalization Schemes for Speaker Verification
TL;DR: This paper reviews how prior knowledge can be included at different normalization levels and the benefit of including knowledge of the target speaker gender and, eventually, of the test segment handset type, with experiments on the Switchboard corpus.
Text-independent speaker verification using support vector machines.
TL;DR: A new feature representation based on GMM is proposed to construct the input vectors to train the SVM to discriminate the true-target speaker access class from the non-target speakers access class.