The performance of voice dialling systems often degrades rapidly as the intensity of the background noise increases. In this paper, we describe a neural network based speech enhancement technique for improving the speech recognition performance of a voice dialling sys-tem in very noisy real world type conditions. The speech samples were recorded in laboratory conditions and after-wards corrupted by adding car noise or babble noise recorded in a cafe. These noise corrupted speech samples were enhanced in cepstral domain by a context dependent multilayer perceptron (MLP) network before performing the recognition using a hidden Markov model (HMM) based speech recognition system. The accuracy of the test set increased 58%, 55% and 46% in the car noise envi-ronments having -5 dB, 0 dB and 5 dB SNRs, respec-tively. The accuracy of the test set increased 44%, 48% and 39% in the babble noise environments having SNR 5 dB, 10 dB and 15 dB, respectively. The accuracy remained approximately same for both car and babble noise environments when having SNR of 20 dB.
Cite as: Haverinen, H., Salmela, P., Häkkinen, J., Lehtokangas, M., Saarinen, J. (1999) MLP network for enhancement of noisy MFCC vectors. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2371-2374, doi: 10.21437/Eurospeech.1999-519
@inproceedings{haverinen99_eurospeech,
author={Hemmo Haverinen and Petri Salmela and Juha Häkkinen and Mikko Lehtokangas and Jukka Saarinen},
title={{MLP network for enhancement of noisy MFCC vectors}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={2371--2374},
doi={10.21437/Eurospeech.1999-519}
}