Statistical Feature Language Model - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2004

Statistical Feature Language Model

Résumé

Statistical language models are widely used in automatic speech recognition in order to constrain the decoding of a sentence. Most of these models derive from the classical n-gram paradigm. However, the production of a word dends on a large set of linguistic features : lexical, syntactic, semantic, etc. Moreover, in some natural languages the gender and number of the left context affect the production of the next word. Therefore, it seems attractive to design a language model based on a variety of word features. We present in this paper a new statistical language model, called Statistical Feature Language Model, SFLM, based on this idea. In SFLM a word is considered as an array of linguistic features, and the model is defined in a way similar to the n-gram model. Experiments carried out for French and show an improvement in terms of perplexity and predicted words.
Fichier principal
Vignette du fichier
salma1.pdf (51.28 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00100021 , version 1 (21-11-2017)

Identifiants

  • HAL Id : inria-00100021 , version 1

Citer

Kamel Smaïli, Salma Jamoussi, David Langlois, Jean-Paul Haton. Statistical Feature Language Model. 8th International Conference on Spoken Language Processing - ICSLP' 2004, 2004, Jeju, South Korea. 4 p. ⟨inria-00100021⟩
136 Consultations
119 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More