7th International Conference on Spoken Language Processing
September 16-20, 2002
Unsupervised adaptation methods have been applied successfully to the acoustic models of speech recognition systems for some time. Relatively little work has been carried out in the area of unsupervised language model adaptation however. The work presented here uses the output of a speech recogniser to adapt the backoff n-gram language model used in the decoding process. We report results for two different methods of language model adaptation, and find that best results are obtained when these two are used in conjunction with one another. The adaptation methods are applied to a Japanese large vocabulary transcription task, for which improvements both in perplexity and word error-rate are achieved.
Bibliographic reference. Niesler, Thomas / Willett, Daniel (2002): "Unsupervised language model adaptation for lecture speech transcription", In ICSLP-2002, 1413-1416.