The minimum Bayes risk (MBR) criterion has previously been applied to the task of speaker adaptation in large vocabulary continuous speech recognition. The success of unsupervised MBR speaker adaptation, however, has been limited by the accuracy of the estimated transcription of the acoustic data. This paper addresses this issue not by improving the accuracy of the estimated transcription but via temporal masking of its erroneous regions.
Cite as: Gibson, M., Hain, T. (2007) Temporal masking for unsupervised minimum Bayes risk speaker adaptation. Proc. Interspeech 2007, 238-241, doi: 10.21437/Interspeech.2007-95
@inproceedings{gibson07_interspeech,
author={Matthew Gibson and Thomas Hain},
title={{Temporal masking for unsupervised minimum Bayes risk speaker adaptation}},
year=2007,
booktitle={Proc. Interspeech 2007},
pages={238--241},
doi={10.21437/Interspeech.2007-95}
}