Ma, N. orcid.org/0000-0002-4112-3109, Marxer, R., Barker, J. orcid.org/0000-0002-1684-5660 et al. (1 more author) (2015) Exploiting synchrony spectra and deep neural networks for noise-robust automatic speech recognition. In: ASRU 2015 Proceedings. 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) , December 13-17 2015, Scottsdale, Arizona, USA. IEEE , pp. 490-495. ISBN 978-1-4799-7291-3
Abstract
This paper presents a novel system that exploits synchrony spectra and deep neural networks (DNNs) for automatic speech recognition (ASR) in challenging noisy environments. Synchrony spectra measure the extent to which each frequency channel in an auditory model is entrained to a particular pitch period, and they are used together with F0 estimates either in a DNN for time-frequency (T-M) mask estimation or to augment the input features for a DNN-based ASR system. The proposed approach was evaluated in the context of the CHiME 3 Challenge. Our experiments show that the synchrony spectra features work best when augmenting the input features to the DNN-based ASR system. Compared to the CHiME-3 baseline system, our best system provides a word error rate (WER) reduction of more than 14% absolute and achieved a WER of 18.56% on the evaluation test set.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. Reproduced in accordance with the publisher's self-archiving policy. |
Keywords: | Deep neural network; noise-robust automatic speech recognition; synchrony spectra; mask estimation |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 18 Aug 2016 08:41 |
Last Modified: | 04 Nov 2016 07:13 |
Published Version: | http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp... |
Status: | Published |
Publisher: | IEEE |
Identification Number: | 10.1109/ASRU.2015.7404835 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:102984 |