In this paper, a new feature extraction methodology based on Wavelet Transforms is examined, which unlike some conventional parameterisation techniques, is flexible enough to cope with the broadly differing characteristics of typical speech signals. A training phase is involved during which the final classifier is invoked to associate a cost function (a proxy for misclassification) with a given resolution. The sub spaces are then searched and pruned to provide a Wavelet Basis best suited to the classification problem. Comparative results are given illustrating some improvement over the Short-Time Fourier Transform using two differing subclasses of speech.
Cite as: Long, C.J., Datta, S. (1998) Discriminant wavelet basis construction for speech recognition. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0802, doi: 10.21437/ICSLP.1998-535
@inproceedings{long98_icslp,
author={Christopher John Long and Sekharajit Datta},
title={{Discriminant wavelet basis construction for speech recognition}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0802},
doi={10.21437/ICSLP.1998-535}
}