This paper describes an approach to increase the noise robustness of automatic speech recognition systems by, transforming the signal after Mel scaled filtering, to make the cumulative density functions of the signal's values in recognition match the ones that where estimated on the training data. The cumulative density functions are approximated using a small number of quantiles. Recognition tests on several databases showed significant reductions of the word error rates. On a real life database recorded in driving cars with a large mismatch between the training and testing conditions the relative reductions of the word error rates where over 60%.
Cite as: Hilger, F., Ney, H. (2001) Quantile based histogram equalization for noise robust speech recognition. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 1135-1138, doi: 10.21437/Eurospeech.2001-285
@inproceedings{hilger01_eurospeech,
author={Florian Hilger and Hermann Ney},
title={{Quantile based histogram equalization for noise robust speech recognition}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={1135--1138},
doi={10.21437/Eurospeech.2001-285}
}