Deviating from the conventional Hidden Markov Model-Multi-Layer Perceptron (HMM-MLP) hybrid paradigm of using MLP for classification, the proposed discriminative MLP technique uses MLP as a mapping module for feature extraction for conventional HMM-based systems. The MLP is discriminatively trained on the phonetically labeled training data to generate the phoneme posterior probabilities. We achieved a relative word error rate reduction of 15-35% on AURORA Phase 2 continuous digit recognition task defined by ETSI.
Cite as: Sivadas, S., Jain, P., Hermansky, H. (2000) Discriminative MLPs in HMM-based recognition of speech in cellular telephony. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 153-156, doi: 10.21437/ICSLP.2000-774
@inproceedings{sivadas00_icslp,
author={Sunil Sivadas and Pratibha Jain and Hynek Hermansky},
title={{Discriminative MLPs in HMM-based recognition of speech in cellular telephony}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 4, 153-156},
doi={10.21437/ICSLP.2000-774}
}