Learning Filterbanks from Raw Speech for Phone Recognition
Neil Zeghidour, Nicolas Usunier, Iasonas Kokkinos, Thomas Schatz, Gabriel Synnaeve, Emmanuel Dupoux
Abstract
We train a bank of complex filters that operates on the raw waveform and is fed into a convolutional neural network for end-to-end phone recognition. These time-domain filterbanks (TD-filterbanks) are initialized as an approximation of mel-filterbanks, and then fine-tuned jointly with the remaining convolutional architecture. We perform phone recognition experiments on TIMIT and show that for several architectures, models trained on TD- filterbanks consistently outperform their counterparts trained on comparable mel-filterbanks. We get our best performance by learning all front-end steps, from pre-emphasis up to averaging. Finally, we observe that the filters at convergence have an asymmetric impulse response, and that some of them remain almost analytic.
BibTeX
@inproceedings{icassp2018_learningfilterba,
title = {Learning Filterbanks from Raw Speech for Phone Recognition},
author = {Neil Zeghidour and Nicolas Usunier and Iasonas Kokkinos and Thomas Schatz and Gabriel Synnaeve and Emmanuel Dupoux},
booktitle = {ICASSP 2018},
year = {2018}
}