Integration of phonological knowledge in a continuous speech recognition system - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 1993

Integration of phonological knowledge in a continuous speech recognition system

Résumé

Building a dictation machine involves the management of linguistic knowledge. We are dealing here with the explicit integration of a phonological module in the automatic dictation machine MAUD, of which a first version has already been implemented [1]. MAUD is made up of three main modules: an acoustic-phonetic decoder, a lexical module and a syntactic module. Some of the problems at the lexical level can be addressed with the help of a phonological module. The one we have developped comprises a set of phonological rules taken from generative phonology [2] in order to transform phonetic forms into phonological ones. The most important problem is to formalize the rules in order to use them in speech recognition. The implementation of these rules leans on IRIT work [3] based on two original notions: multi-pronunciation groups (mpg's) and contextual phonological group (cpg's). Experimental results illustrate the impact of phonological knowledge in the overall recognition process of a dictation machine
Fichier non déposé

Dates et versions

hal-00589106 , version 1 (27-04-2011)

Identifiants

  • HAL Id : hal-00589106 , version 1

Citer

Roselyne Nguyen, Kamel Smaïli, Jean-Paul Haton, Guy Pérennou. Integration of phonological knowledge in a continuous speech recognition system. European conference on speech communication and technology, Sep 1993, Berlin, Germany. pp.2191-2194. ⟨hal-00589106⟩
147 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More