Sixth International Conference on Spoken Language Processing
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.
Bibliographic reference. Sivadas, Sunil / Jain, Pratibha / Hermansky, Hynek (2000): "Discriminative MLPs in HMM-based recognition of speech in cellular telephony", In ICSLP-2000, vol.4, 153-156.