ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Unsupervised estimation of the language model scaling factor

Christopher M. White, Ariya Rastrow, Sanjeev Khudanpur, Frederick Jelinek

This paper addresses the adjustment of the language model (LM) scaling factor of an automatic speech recognition (ASR) system for a new domain using only un-transcribed speech. The main idea is to replace the (unavailable) reference transcript with an automatic transcript generated by an independent ASR system, and adjust parameters using this sloppy reference. It is shown that despite its fairly high error rate (ca. 35%), choosing the scaling factor to minimize disagreement with the erroneous transcripts is still an effective recipe for model selection. This effectiveness is demonstrated by adjusting an ASR system trained on Broadcast News to transcribe the MIT Lectures corpus. An ASR system for telephone speech produces the sloppy reference, and optimizing towards it yields a nearly optimal LM scaling factor for the MIT Lectures corpus.

doi: 10.21437/Interspeech.2009-346

Cite as: White, C.M., Rastrow, A., Khudanpur, S., Jelinek, F. (2009) Unsupervised estimation of the language model scaling factor. Proc. Interspeech 2009, 1195-1198, doi: 10.21437/Interspeech.2009-346

  author={Christopher M. White and Ariya Rastrow and Sanjeev Khudanpur and Frederick Jelinek},
  title={{Unsupervised estimation of the language model scaling factor}},
  booktitle={Proc. Interspeech 2009},