Generalized Driven Decoding for Speech Recognition System Combination

Abstract : Driven Decoding Algorithm (DDA) is initially an integrated approach for the combination of 2 speech recognition (ASR) systems. It consists in guiding the search algorithm of a primary ASR system by the one-best hypothesis of an auxiliary system. In this paper , we generalize DDA to confusion-network driven decoding and we propose new combination schemes for multiple system combination. Since previous experiments involved 2 ASR systems on broadcast news data, the proposed extended DDA is evaluated using 3 ASR systems from different labs. Results show that generalized-DDA outperforms significantly ROVER method: we obtain a 15.7% relative word error rate improvement with respect to the best single system, as opposed to 8.5% with the ROVER combination.
Type de document :
Communication dans un congrès
IEEE International Conference on Acoustics, Speech and Signal Processing , Mar 2008, Las Vegas, United States
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01318069
Contributeur : Bibliothèque Universitaire Déposants Hal-Avignon <>
Soumis le : jeudi 23 novembre 2017 - 10:53:38
Dernière modification le : vendredi 16 novembre 2018 - 01:23:46

Fichier

Benj_ICASSP08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01318069, version 1

Citation

Benjamin Lecouteux, Georges Linarès, Yannick Estève, Guillaume Gravier. Generalized Driven Decoding for Speech Recognition System Combination. IEEE International Conference on Acoustics, Speech and Signal Processing , Mar 2008, Las Vegas, United States. 〈hal-01318069〉

Partager

Métriques

Consultations de la notice

498

Téléchargements de fichiers

39