Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Context-Sensitive Statistical Language Modeling

Alexander Gruenstein, Chao Wang, Stephanie Seneff

Massachusetts Institute of Technology, USA

We present context-sensitive dynamic classes - a novel mechanism for integrating contextual information from spoken dialogue into a class n-gram language model. We exploit the dialogue system's information state to populate dynamic classes, thus percolating contextual constraints to the recognizer's language model in real time. We describe a technique for training a language model incorporating context-sensitive dynamic classes which considerably reduces word error rate under several conditions. Significantly, our technique does not partition the language model based on potentially artificial dialogue state distinctions; rather, it accommodates both strong and weak expectations via dynamic manipulation of a single model.

Full Paper

Bibliographic reference.  Gruenstein, Alexander / Wang, Chao / Seneff, Stephanie (2005): "Context-sensitive statistical language modeling", In INTERSPEECH-2005, 17-20.