A system for discriminative feature and model design is presented for automatic speech recognition. Training based on minimum classification error using a single objective function is applied for designing a set of parallel networks performing feature transformation and a set of hidden Markov models performing speech recognition. This paper compares the use of linear and non-linear functional transformations when applied to conventional recognition features, such as spectrum or cepstrum. It also provides a framework for integrated feature and model training when using class-specific transformations. Experimental results on telephone-based connected digit recognition are presented.
Cite as: Rahim, M., Bengio, Y., LeCun, Y. (1997) Discriminative feature and model design for automatic speech recognition. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 75-78, doi: 10.21437/Eurospeech.1997-46
@inproceedings{rahim97_eurospeech,
author={Mazin Rahim and Yoshua Bengio and Yann LeCun},
title={{Discriminative feature and model design for automatic speech recognition}},
year=1997,
booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
pages={75--78},
doi={10.21437/Eurospeech.1997-46}
}