LIUM and CRIM ASR System Combination for the REPERE Evaluation Campaign

Anthony Rousseau 1 Gilles Boulianne 2 Paul Deléglise 1 Yannick Estève 1 Vishwa Gupta 2 Sylvain Meignier 1
1 LIUM - Laboratoire d'Informatique de l'Université du Mans
2 CRIM - Centre de Recherche Informatique de Montréal
Abstract : This paper describes the ASR system proposed by the SODA consortium to participate in the ASR task of the French REPERE evaluation campaign. The official test REPERE corpus is composed of TV shows. The entire ASR system was produced by combining two ASR systems built by two members of the consortium. Each ASR system has some specificities: one uses an i-vector-based speaker adaptation of deep neural networks for acoustic modeling, while the other one rescores word-lattices with continuous space language models. The entire ASR system won the REPERE evaluation campaign on the ASR task. On the REPERE test corpus, this composite ASR system reaches a word error rate of 13.5 %.
Type de document :
Communication dans un congrès
17th International Conference on Text, Speech and Dialogue, 2014, Brno, Czech Republic. pp.441 - 448, 2014, International Conference on Text, Speech, and Dialogue. 〈10.1007/978-3-319-10816-2_53〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger
https://hal.archives-ouvertes.fr/hal-01450629
Contributeur : Hakim Amokrane <>
Soumis le : lundi 3 avril 2017 - 21:47:17
Dernière modification le : mardi 21 novembre 2017 - 15:40:12
Document(s) archivé(s) le : mardi 4 juillet 2017 - 14:54:38

Fichier

640.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

UNIV-LEMANS | LIUM | LIUM-LST

Citation

Anthony Rousseau, Gilles Boulianne, Paul Deléglise, Yannick Estève, Vishwa Gupta, et al.. LIUM and CRIM ASR System Combination for the REPERE Evaluation Campaign. 17th International Conference on Text, Speech and Dialogue, 2014, Brno, Czech Republic. pp.441 - 448, 2014, International Conference on Text, Speech, and Dialogue. 〈10.1007/978-3-319-10816-2_53〉. 〈hal-01450629〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

213

Téléchargements de fichiers

83

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD