A Level-Building Top-Down Parsing Algorithm for Context-Free Grammars in Continuous Speech Recognition

François Charpillet 1 Joseph Di Martino 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We present in this paper a dynamic programming parsing algorithm in the framework of continuous speech recognition. The language of the applications we want to deal with, is described using a context-free grammar given in Greibach normal form. The parsing algorithm follows the level-building technique and finds the p sentences matching the speech signal with the best scores. Our approach is different from the existing ones, in the sense that it is suboptimal but with a lower order of complexity. By suboptimal we mean that a syntactically correct sentence with a score belonging to the p best ones can be missed by our algorithm. This leads us to discuss the trade-off between quality of results on the one hand and the complexity of the algorithm on the other hand. As a conclusion, we will see that in practice, our approach yields results of comparable quality in spite of their slight theoritical corruption.
Type de document :
Communication dans un congrès
EUROSPEECH - Third European Conference on Speech Communication and Technology - 1993, Sep 1993, Berlin, Germany. pp.1947-1949, 1993
Liste complète des métadonnées

https://hal.inria.fr/hal-00835135
Contributeur : Joseph Di Martino <>
Soumis le : mardi 18 juin 2013 - 10:19:58
Dernière modification le : jeudi 11 janvier 2018 - 06:19:56

Identifiants

  • HAL Id : hal-00835135, version 1

Collections

Citation

François Charpillet, Joseph Di Martino. A Level-Building Top-Down Parsing Algorithm for Context-Free Grammars in Continuous Speech Recognition. EUROSPEECH - Third European Conference on Speech Communication and Technology - 1993, Sep 1993, Berlin, Germany. pp.1947-1949, 1993. 〈hal-00835135〉

Partager

Métriques

Consultations de la notice

158