The purpose of this work is to improve the automatic speech recognition of confusable words. The database considered is the American-English alphanumeric vocabulary. Our study proposes a new method using artificial neural networks and reports a comparison with a global method using hidden Markov models (HMM). The new method is based on the search for discriminative frames which bear the distinction between the confusable words. The tests, conducted on normal speech and Lombard speech with and without additive noise, show a general improvement of the recognition accuracy.
Cite as: Anglade, Y., Fohr, D., Junqua, J.-C. (1992) A robust discrimination method based on selectively trained neural networks. Proc. ETRW on Speech Processing in Adverse Conditions, 175-178
@inproceedings{anglade92_spac,
author={Yolande Anglade and Dominique Fohr and Jean-Claude Junqua},
title={{A robust discrimination method based on selectively trained neural networks}},
year=1992,
booktitle={Proc. ETRW on Speech Processing in Adverse Conditions},
pages={175--178}
}