This is the latest version of this eprint.
Ravenscroft, W., Goetze, S. and Hain, T. (2022) Utterance weighted multi-dilation temporal convolutional networks for monaural speech dereverberation. In: Proceedings of 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), 05-08 Sep 2022, Bamberg, Germany. Institute of Electrical and Electronics Engineers (IEEE) ISBN 9781665468688
Abstract
Speech dereverberation is an important stage in many speech technology applications. Recent work in this area has been dominated by deep neural network models. Temporal convolutional networks (TCNs) are deep learning models that have been proposed for sequence modelling in the task of dereverberating speech. In this work a weighted multi-dilation depthwise-separable convolution is proposed to replace standard depthwise-separable convolutions in TCN models. This proposed convolution enables the TCN to dynamically focus on more or less local information in its receptive field at each convolutional block in the network. It is shown that this weighted multi-dilation temporal convolutional network (WD-TCN) consistently outperforms the TCN across various model configurations and using the WD-TCN model is a more parameter-efficient method to improve the performance of the model than increasing the number of convolutional blocks. The best performance improvement over the baseline TCN is 0.55 dB scale-invariant signal-to-distortion ratio (SISDR) and the best performing WD-TCN model attains 12.26 dB SISDR on the WHAMR dataset.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2022 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: | speech dereverberation; temporal convolutional network; speech enhancement; receptive field; deep neural network |
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: | 01 Sep 2022 08:30 |
Last Modified: | 17 Oct 2023 00:13 |
Status: | Published |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Refereed: | Yes |
Identification Number: | 10.1109/IWAENC53105.2022.9914752 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:190285 |
Available Versions of this Item
-
Utterance weighted multi-dilation temporal convolutional networks for monaural speech dereverberation. (deposited 05 Aug 2022 06:37)
- Utterance weighted multi-dilation temporal convolutional networks for monaural speech dereverberation. (deposited 01 Sep 2022 08:30) [Currently Displayed]