A Multi-Perspective evaluation of the NESPOLE! Speech-to-Speech Translation System

Abstract : Performance and usability of realworld speech-to-speech translation systems, like the one developed within the NESPOLE! project, are affected by several aspects that go beyong the pure translation quality provided by the underlying components of the system. In this paper we describe these aspects as perspectives along wich we have evaluated the NESPOLE! system. Four main issues are investigated (1) assessing system performance under various networtk traffic conditions; (2) a study on the usage and utility of multi-modality in the context of multilingual communication; (3) a comparaison of the features of the individual speech recognition engines. and (4) an end-to-end evaluation of the system.
Type de document :
Communication dans un congrès
ACL'02 workshop on Speech-to-Speech Translation: Algorithms and Systems, Jun 2002, Philadelphia - Pennsylvania, United States. 9 p., 2002
Liste complète des métadonnées

https://hal.inria.fr/inria-00326403
Contributeur : Dominique Vaufreydaz <>
Soumis le : jeudi 2 octobre 2008 - 21:33:38
Dernière modification le : vendredi 3 octobre 2008 - 16:59:58
Document(s) archivé(s) le : vendredi 4 juin 2010 - 12:09:06

Fichier

Lavie02b.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00326403, version 1

Collections

UGA

Citation

Alon Lavie, Florian Metze, Roldano Cattoni, Erica Costantini, Susanne Burger, et al.. A Multi-Perspective evaluation of the NESPOLE! Speech-to-Speech Translation System. ACL'02 workshop on Speech-to-Speech Translation: Algorithms and Systems, Jun 2002, Philadelphia - Pennsylvania, United States. 9 p., 2002. 〈inria-00326403〉

Partager

Métriques

Consultations de la notice

99

Téléchargements de fichiers

190