An Hybrid Language Model for a Continuous Dictation Prototype

Kamel Smaïli (1) , Imed Zitouni (2) , François Charpillet (3) , Jean-Paul Haton (2)

1 SMarT - Statistical Machine Translation and Speech Modelization and Text
2 PAROLE - Analysis, perception and recognition of speech
3 MAIA - Autonomous intelligent machine

This paper describes the combination of a stochastic language model and a formal grammar modeled such as a unification grammar. The stochastic model is trained over 42 million words extracted from Le Monde newspaper. The stochastic model is based on smoothed 3-gram and 3-class. The 3-class model is represented by a Markov chain made up of four states. Several experiments have been done to state which values are the best for specific training and test corpus. Experiments indicate that the unification grammar reduces strongly the number of hypothesis (sentences) produced by the stochastic model.

Mots clés: Hybrid language model; Unification grammar; N-best sentences; Tagging

Domaines: Informatique et langage [cs.CL]

Kamel Smaïli, Imed Zitouni, François Charpillet, Jean-Paul Haton. An Hybrid Language Model for a Continuous Dictation Prototype. 5th European Conference on Speech Communication and Technology, Sep 1997, Rhodes, Greece. ⟨hal-01112905⟩