Communication Dans Un Congrès Année : 2009

Constraint selection for topic-based MDI adaptation of language models

Résumé

Constraint selection for topic-based MDI adaptation of language models This paper presents an unsupervised topic-based language model adaptation method which specializes the standard minimum information discrimination approach by identifying and combining topic-specific features. By acquiring a topic terminology from a thematically coherent corpus, language model adaptation is restrained to the sole probability re-estimation of n-grams ending with some topic-specific words, keeping other probabilities untouched. Experiments are carried out on a large set of spoken documents about various topics. Results show significant perplexity and recognition improvements which outperform results of classical adaptation techniques.

Fichier principal
Vignette du fichier
LeGS2009.pdf (165.15 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-00760610 , version 1 (04-12-2012)

Licence

Identifiants

  • HAL Id : hal-00760610 , version 1

Citer

Gwénolé Lecorvé, Guillaume Gravier, Pascale Sébillot. Constraint selection for topic-based MDI adaptation of language models. 10th Annual Conference of the International Speech Communication Association, Interspeech'09, Sep 2009, Brighton, United Kingdom. pp.368--371. ⟨hal-00760610⟩
328 Consultations
273 Téléchargements

Partager

  • More