Additive bias compensation is a simple and effective technique to overcome the performance degradation caused by acoustic mismatch in speech recognition systems. Bias is usually estimated in a batch mode, assuming that its parameters are constant for the whole utterance. This paper develops a new sequential algorithm for additive bias estimation, which can potentially track time varying mismatch effects within a test utterance. Relation to recursive Kullback-Leibler technique is pointed out, and the method is tested using computer simulations and speech recognition experiments. Significant performance improvements in the recognition rate are obtained for supervised adaptation.
Cite as: Afify, M. (1999) Sequential bias compensation for robust speech recognition. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2821-2824, doi: 10.21437/Eurospeech.1999-623
@inproceedings{afify99_eurospeech,
author={Mohamed Afify},
title={{Sequential bias compensation for robust speech recognition}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={2821--2824},
doi={10.21437/Eurospeech.1999-623}
}