INTERSPEECH 2009
10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

A Back-Off Discriminative Acoustic Model for Automatic Speech Recognition

Hung-An Chang, James R. Glass

MIT, USA

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.

Full Paper

Bibliographic reference.  Chang, Hung-An / Glass, James R. (2009): "A back-off discriminative acoustic model for automatic speech recognition", In INTERSPEECH-2009, 232-235.