In this paper we propose a back-off discriminative acoustic model for Automatic Speech Recognition (ASR). We use a set of broad phonetic classes to divide the classification problem originating from context-dependent modeling into a set of sub-problems. By appropriately combining the scores from classifiers designed for the sub-problems, we can guarantee that the back-off acoustic score for different context-dependent units will be different. The back-off model can be combined with discriminative training algorithms to further improve the performance. Experimental results on a large vocabulary lecture transcription task show that the proposed back-off discriminative acoustic model has more than a 2.0% absolute word error rate reduction compared to clustering-based acoustic model.
Cite as: Chang, H.-A., Glass, J.R. (2009) A back-off discriminative acoustic model for automatic speech recognition. Proc. Interspeech 2009, 232-235, doi: 10.21437/Interspeech.2009-83
@inproceedings{chang09_interspeech,
author={Hung-An Chang and James R. Glass},
title={{A back-off discriminative acoustic model for automatic speech recognition}},
year=2009,
booktitle={Proc. Interspeech 2009},
pages={232--235},
doi={10.21437/Interspeech.2009-83}
}