Constraint selection for topic-based MDI adaptation of language models

Gwénolé Lecorvé (1) , Guillaume Gravier (1) , Pascale Sébillot (1)

1 TEXMEX - Multimedia content-based indexing

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.

Mots clés: language model adaptation; topic terminology; minimum discrimination information; speech recognition

Domaines: Traitement du texte et du document

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⟩