Complex valued neural networks for audio signal processing
Complex valued neural networks for audio signal processing
Complex-valued neural networks (CVNNs) were first developed some time ago, but there has recently been renewed interest in extending currently used neural network architectures to enable the use of complex valued data. This paper investigates the benefits of CVNNs compared to conventional real-valued neural networks (RVNNs) for speech enhancement problems. Clean speech signals are mixed with background noise at different signal-to-noise ratios and the networks are then trained to denoise the speech signals in the frequency domain. For the comparison of separation performance, the properties of the complex Ideal Ratio Mask (cIRM) previously proposed are investigated and some preliminary results are discussed with an emphasis on future potential applications.
Paul, Vlad S.
a643f880-7e70-4ae0-a27b-4e77c3c451de
Nelson, Philip A.
5c6f5cc9-ea52-4fe2-9edf-05d696b0c1a9
16 November 2021
Paul, Vlad S.
a643f880-7e70-4ae0-a27b-4e77c3c451de
Nelson, Philip A.
5c6f5cc9-ea52-4fe2-9edf-05d696b0c1a9
Paul, Vlad S. and Nelson, Philip A.
(2021)
Complex valued neural networks for audio signal processing.
In Reproduced Sound 2021: You''re on Mute - The Importance of Audio.
vol. 43,
Institute of Acoustics..
Record type:
Conference or Workshop Item
(Paper)
Abstract
Complex-valued neural networks (CVNNs) were first developed some time ago, but there has recently been renewed interest in extending currently used neural network architectures to enable the use of complex valued data. This paper investigates the benefits of CVNNs compared to conventional real-valued neural networks (RVNNs) for speech enhancement problems. Clean speech signals are mixed with background noise at different signal-to-noise ratios and the networks are then trained to denoise the speech signals in the frequency domain. For the comparison of separation performance, the properties of the complex Ideal Ratio Mask (cIRM) previously proposed are investigated and some preliminary results are discussed with an emphasis on future potential applications.
This record has no associated files available for download.
More information
Published date: 16 November 2021
Additional Information:
Publisher Copyright:
© 2021 Institute of Acoustics. All rights reserved.
Copyright:
Copyright 2022 Elsevier B.V., All rights reserved.
Venue - Dates:
Reproduced Sound 2021: You''re on Mute - The Importance of Audio, , Bristol, United Kingdom, 2021-11-16 - 2021-11-18
Identifiers
Local EPrints ID: 457352
URI: http://eprints.soton.ac.uk/id/eprint/457352
ISSN: 1478-6095
PURE UUID: 5ba389f3-4a73-4705-a158-51d211f27400
Catalogue record
Date deposited: 01 Jun 2022 16:45
Last modified: 21 Feb 2024 03:03
Export record
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
