EUVIMEDEUVIMED entdecken
Crossref

Room impulse response reconstruction with physics-informed deep learning

Xenofon Karakonstantis iD, Diego Caviedes-Nozal, Antoine Richard, Efren Fernandez-Grande iD

The Journal of the Acoustical Society of America · 01.02.2024 · 155 (2) · 1048-1059

DOI: 10.1121/10.0024750 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 06.02.2024. Verfasst von Xenofon Karakonstantis und 3 weiteren Autor:innen. Beteiligte Einrichtung: Acoustic Technology, Department of Electrical & Photonics Engineering, Technical University of Denmark, Kongens Lyngby, Denmark. Die Arbeit wurde bisher 73-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Villum Fonden.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A method is presented for estimating and reconstructing the sound field within a room using physics-informed neural networks. By incorporating a limited set of experimental room impulse responses as training data, this approach combines neural network processing capabilities with the underlying physics of sound propagation, as articulated by the wave equation. The network's ability to estimate particle velocity and intensity, in addition to sound pressure, demonstrates its capacity to represent the flow of acoustic energy and completely characterise the sound field with only a few measurements. Additionally, an investigation into the potential of this network as a tool for improving acoustic simulations is conducted. This is due to its proficiency in offering grid-free sound field mappings with minimal inference time. Furthermore, a study is carried out which encompasses comparative analyses against current approaches for sound field reconstruction. Specifically, the proposed approach is evaluated against both data-driven techniques and elementary wave-based regression methods. The results demonstrate that the physics-informed neural network stands out when reconstructing the early part of the room impulse response, while simultaneously allowing for complete sound field characterisation in the time domain.

Autor:innen und Institutionen

  • Acoustic Technology, Department of Electrical & Photonics Engineering, Technical University of Denmark, Kongens Lyngby, Denmark.
  • Audio Research, GN Audio A/S & Jabra, Ballerup, Denmark.
  • Odeon A/S, Kongens Lyngby, Denmark.

ORCID-Profile: Xenofon Karakonstantis, Efren Fernandez-Grande

Förderung

  • Villum Fonden

Zitieren

APA

Karakonstantis, X., Caviedes-Nozal, D., Richard, A., & Fernandez-Grande, E. (2024). Room impulse response reconstruction with physics-informed deep learning. The Journal of the Acoustical Society of America, 155(2), 1048-1059. https://doi.org/10.1121/10.0024750

Vancouver

Karakonstantis X, Caviedes-Nozal D, Richard A, Fernandez-Grande E. Room impulse response reconstruction with physics-informed deep learning. The Journal of the Acoustical Society of America. 2024;155(2):1048-1059. doi:10.1121/10.0024750

BibTeX
@article{Karakonstantis2024,
  author = {Karakonstantis, Xenofon and Caviedes-Nozal, Diego and Richard, Antoine and Fernandez-Grande, Efren},
  title = {Room impulse response reconstruction with physics-informed deep learning},
  journal = {The Journal of the Acoustical Society of America},
  year = {2024},
  volume = {155},
  number = {2},
  pages = {1048--1059},
  doi = {10.1121/10.0024750}
}
Kostenlos starten →