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.
Complete list of metadatas

https://hal.inria.fr/hal-00835135
Contributor : Joseph Di Martino <>
Submitted on : Tuesday, June 18, 2013 - 10:19:58 AM
Last modification on : Thursday, January 11, 2018 - 6:19:56 AM

Identifiers

  • 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. ⟨hal-00835135⟩

Share

Metrics

Record views

262