Computer Science Department
School of Computer Science, Carnegie Mellon University


Large-scale Topic Detection and Language Model Adaptation

Kristie Seymore, Ronald Rosenfeld

June 1997

Keywords: Speech recognition, statistical language modeling, topic detection, topic adaptation, document clustering

The subject matter of any conversation or document can typically be described as some combination of elemental topics. We have developed a language model adaptation scheme that takes a piece of text, chooses the most similar topic clusters from a set of over 5000 elemental topics, and uses topic specific language models built from the topic clusters to rescore N-best lists. We are able to achieve a 15% reduction in perplexity and a small improvement in word error rate by using this adaptation. We also investigate the use of a topic tree, where the amount of training data for a specific topic can be judiciously increased in cases where the elemental topic cluster has too few word tokens to build a reliably smoothed and representative language model. Our system is able to fine-tune topic adaptation by interpolating models chosen from thousands of topics, allowing for adaptation to unique, previously unseen combinations of subjects.

20 pages

Return to: SCS Technical Report Collection
School of Computer Science homepage

This page maintained by