The University of Southampton
University of Southampton Institutional Repository

Design of real and complex recurrent neural networks for sound source localisation

Design of real and complex recurrent neural networks for sound source localisation
Design of real and complex recurrent neural networks for sound source localisation
This study explores a pruning technique based on the singular value decomposition (SVD) for both real- and complex-valued recurrent neural networks (RNNs). Building on prior work on multilayer perceptrons (MLPs), the method reduces hidden-layer dimensions during training to reduce computation with minimal performance loss. Challenges unique to RNNs are addressed and compared to those of MLPs. Pruned models are compared with original architectures and a benchmark pruning method in a sound source localisation task. Results show real- and complex-valued RNNs can retain strong performance while using substantially fewer computational resources.
2691-1191
Paul, Vlad S.
3f46807b-cda2-4818-ba70-71bfd26a1a92
Nelson, Philip A.
5c6f5cc9-ea52-4fe2-9edf-05d696b0c1a9
Paul, Vlad S.
3f46807b-cda2-4818-ba70-71bfd26a1a92
Nelson, Philip A.
5c6f5cc9-ea52-4fe2-9edf-05d696b0c1a9

Paul, Vlad S. and Nelson, Philip A. (2026) Design of real and complex recurrent neural networks for sound source localisation. JASA Express Letters, 6 (3), [034801]. (doi:10.1121/10.0042761).

Record type: Article

Abstract

This study explores a pruning technique based on the singular value decomposition (SVD) for both real- and complex-valued recurrent neural networks (RNNs). Building on prior work on multilayer perceptrons (MLPs), the method reduces hidden-layer dimensions during training to reduce computation with minimal performance loss. Challenges unique to RNNs are addressed and compared to those of MLPs. Pruned models are compared with original architectures and a benchmark pruning method in a sound source localisation task. Results show real- and complex-valued RNNs can retain strong performance while using substantially fewer computational resources.

Text
journal.pcbi.1013989 - Version of Record
Available under License Creative Commons Attribution.
Download (2MB)

More information

Accepted/In Press date: 12 February 2026
Published date: 2 March 2026

Identifiers

Local EPrints ID: 510240
URI: http://eprints.soton.ac.uk/id/eprint/510240
ISSN: 2691-1191
PURE UUID: f60aae84-72fc-467d-85b3-06a28749f697
ORCID for Vlad S. Paul: ORCID iD orcid.org/0000-0002-5562-6102
ORCID for Philip A. Nelson: ORCID iD orcid.org/0000-0002-9563-3235

Catalogue record

Date deposited: 24 Mar 2026 17:34
Last modified: 25 Mar 2026 03:15

Export record

Altmetrics

Contributors

Author: Vlad S. Paul ORCID iD

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

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×