10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

Constraint Selection for Topic-Based MDI Adaptation of Language Models

Gwénolé Lecorvé, Guillaume Gravier, Pascale Sébillot

IRISA, France

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.

Full Paper

Bibliographic reference.  Lecorvé, Gwénolé / Gravier, Guillaume / Sébillot, Pascale (2009): "Constraint selection for topic-based MDI adaptation of language models", In INTERSPEECH-2009, 368-371.