Speaker verification using Large Margin GMM discriminative training

Abstract : Gaussian mixture models (GMM) have been widely and successfully used in speaker recognition during the last decades. They are generally trained using the generative criterion of maximum likelihood estimation. In an earlier work, we proposed an algorithm for discriminative training of GMM with diagonal covariances under a large margin criterion. In this paper, we present a new version of this algorithm which has the major advantage of being computationally highly efficient. The resulting algorithm is thus well suited to handle large scale databases. To show the effectiveness of the new algorithm, we carry out a full NIST speaker verification task using NISTSRE' 2006 data. The results show that our system outperforms the baseline GMM, and with high computational efficiency.
Type de document :
Communication dans un congrès
International Conference on Multimedia Computing and Systems (ICMCS), Apr 2011, Ouarzazate, Morocco. 2011
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00647232
Contributeur : Khalid Daoudi <>
Soumis le : jeudi 1 décembre 2011 - 16:50:49
Dernière modification le : mercredi 12 septembre 2018 - 17:46:02
Document(s) archivé(s) le : vendredi 2 mars 2012 - 02:35:24

Fichier

ICMCS-2011.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00647232, version 1

Collections

Citation

Reda Jourani, Khalid Daoudi, Régine André-Obrecht, Driss Aboutajdine. Speaker verification using Large Margin GMM discriminative training. International Conference on Multimedia Computing and Systems (ICMCS), Apr 2011, Ouarzazate, Morocco. 2011. 〈hal-00647232〉

Partager

Métriques

Consultations de la notice

460

Téléchargements de fichiers

186