Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Sound Field Estimation Using Deep Kernel Learning Regularized by the Wave Equation

Sundstrom, David LU ; Koyama, Shoichi and Jakobsson, Andreas LU orcid (2024) 18th International Workshop on Acoustic Signal Enhancement, IWAENC 2024 p.319-323
Abstract

In this work, we introduce a spatio-temporal kernel for Gaussian process (GP) regression-based sound field estimation. Notably, GPs have the attractive property that the sound field is a linear function of the measurements, allowing the field to be estimated efficiently from distributed microphone measurements. However, to ensure analytical tractability, most existing kernels for sound field estimation have been formulated in the frequency domain, formed independently for each frequency. To address the analytical intractability of spatio-temporal kernels, we here propose to instead learn the kernel directly from data by the means of deep kernel learning. Furthermore, to improve the generalization of the deep kernel, we propose a method... (More)

In this work, we introduce a spatio-temporal kernel for Gaussian process (GP) regression-based sound field estimation. Notably, GPs have the attractive property that the sound field is a linear function of the measurements, allowing the field to be estimated efficiently from distributed microphone measurements. However, to ensure analytical tractability, most existing kernels for sound field estimation have been formulated in the frequency domain, formed independently for each frequency. To address the analytical intractability of spatio-temporal kernels, we here propose to instead learn the kernel directly from data by the means of deep kernel learning. Furthermore, to improve the generalization of the deep kernel, we propose a method for regularizing the learning process using the wave equation. The representational advantages of the deep kernel and the improved generalization obtained by using the wave equation regularization are illustrated using numerical simulations.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
deep kernel learning, Gaussian processes, Sound field estimation, wave equation
host publication
2024 18th International Workshop on Acoustic Signal Enhancement, IWAENC 2024 - Proceedings
pages
5 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
18th International Workshop on Acoustic Signal Enhancement, IWAENC 2024
conference location
Aalborg, Denmark
conference dates
2024-09-09 - 2024-09-12
external identifiers
  • scopus:85207224693
ISBN
9798350361858
DOI
10.1109/IWAENC61483.2024.10694575
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2024 IEEE.
id
1b927f78-b352-4e14-b85a-e9bb2276f060
date added to LUP
2024-11-15 15:38:28
date last changed
2025-04-04 14:48:09
@inproceedings{1b927f78-b352-4e14-b85a-e9bb2276f060,
  abstract     = {{<p>In this work, we introduce a spatio-temporal kernel for Gaussian process (GP) regression-based sound field estimation. Notably, GPs have the attractive property that the sound field is a linear function of the measurements, allowing the field to be estimated efficiently from distributed microphone measurements. However, to ensure analytical tractability, most existing kernels for sound field estimation have been formulated in the frequency domain, formed independently for each frequency. To address the analytical intractability of spatio-temporal kernels, we here propose to instead learn the kernel directly from data by the means of deep kernel learning. Furthermore, to improve the generalization of the deep kernel, we propose a method for regularizing the learning process using the wave equation. The representational advantages of the deep kernel and the improved generalization obtained by using the wave equation regularization are illustrated using numerical simulations.</p>}},
  author       = {{Sundstrom, David and Koyama, Shoichi and Jakobsson, Andreas}},
  booktitle    = {{2024 18th International Workshop on Acoustic Signal Enhancement, IWAENC 2024 - Proceedings}},
  isbn         = {{9798350361858}},
  keywords     = {{deep kernel learning; Gaussian processes; Sound field estimation; wave equation}},
  language     = {{eng}},
  pages        = {{319--323}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Sound Field Estimation Using Deep Kernel Learning Regularized by the Wave Equation}},
  url          = {{http://dx.doi.org/10.1109/IWAENC61483.2024.10694575}},
  doi          = {{10.1109/IWAENC61483.2024.10694575}},
  year         = {{2024}},
}