A Hierarchical Approach for Topic Identification - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2001

A Hierarchical Approach for Topic Identification

Résumé

This paper focuses on language model adaptation, and more especially on topic identification (TID) for Automatic Speech Recognition (ASR). The structure of a set of topics is redefined by the introduction of a hierarchy. TID models may then make use of the semantic relationships between parent and son nodes of the topic-tree. The originality of the approach presented in this article lies in the allocation of a unique vocabulary to brother nodes, which rests on the use of two backing-off levels. In comparison with TID performance when using a non-hierarchical approach, results encourage us to carry on in this way.

Domaines

Autre [cs.OH]
Fichier principal
Vignette du fichier
A01-R-342.pdf (70.66 Ko) Télécharger le fichier
Loading...

Dates et versions

inria-00107536 , version 1 (19-10-2006)

Licence

Domaine public

Identifiants

  • HAL Id : inria-00107536 , version 1

Citer

Brigitte Bigi, Armelle Brun, Kamel Smaïli, Jean-Paul Haton. A Hierarchical Approach for Topic Identification. Proceedings of the international workshop Speech and Computer - SPECOM'01, Nov 2001, Moscow, Russia, France. 4 p. ⟨inria-00107536⟩
170 Consultations
113 Téléchargements

Partager

Gmail Facebook X LinkedIn More