Zeghidour, N;
Usunier, N;
Kokkinos, I;
Schatz, T;
Synnaeve, G;
Dupoux, E;
(2018)
Learning Filterbanks from Raw Speech for Phone Recognition.
In:
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
(pp. pp. 5509-5513).
IEEE
Preview |
Text
1711.01161.pdf - Accepted Version Download (772kB) | Preview |
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.
Type: | Proceedings paper |
---|---|
Title: | Learning Filterbanks from Raw Speech for Phone Recognition |
Event: | ICASSP 2018, International Conference on Acoustics, Speech and Signal Processing, 15-20 April 2018, Calgary, Canada |
ISBN-13: | 978-1-5386-4658-8 |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1109/ICASSP.2018.8462015 |
Publisher version: | https://doi.org/10.1109/ICASSP.2018.8462015 |
Language: | English |
Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
Keywords: | Convolution, Computer architecture, Speech recognition, Time-domain analysis, Scattering, Training, Standards |
UCL classification: | UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10060972 |
Archive Staff Only
![]() |
View Item |