ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition April 13-16, 2003 Tokyo Institute of Technology, Tokyo, Japan

Unsupervised Language Model Adaptation for Lecture Speech Recognition

Hiroaki Nanjo, Tatsuya Kawahara

School of Informatics, Kyoto University, Japan

This paper addresses speaker adaptation of language model in large vocabulary spontaneous speech recognition. In spontaneous speech, the expression and pronunciation of words vary a lot depending on the speaker and topic. Therefore, we present unsupervised methods of language model adaptation to a specific speaker by (1) making direct use of the initial recognition result for generating an enhanced model, and (2) selecting similar texts, utterance by utterance, based on the model. We also investigate the pronunciation variation modeling and its adaptation in the same framework. It is confirmed that all proposed adaptation methods and their combinations reduced the perplexity and word error rate in transcription of real lectures.

Full Paper

Bibliographic reference.  Nanjo, Hiroaki / Kawahara, Tatsuya (2003): "Unsupervised language model adaptation for lecture speech recognition", in SSPR-2003, paper MAP10.