EUVIMEDEUVIMED entdecken
Crossref

Sound-field-projection synthesis using latent diffusion model for acousto-optic reconstruction

Risako Tanigawa iD, Kenji Ishikawa iD, Noboru Harada iD, Yasuhiro Oikawa iD

The Journal of the Acoustical Society of America · 01.05.2026 · 159 (5) · 3858-3869

DOI: 10.1121/10.0043764 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 05.05.2026. Verfasst von Risako Tanigawa und 3 weiteren Autor:innen. Beteiligte Einrichtung: Communication Science Laboratories, NTT, Inc., 3-1 Morinosato-Wakamiya, Atsugi, Kanagawa 243-0198, Japan. Die Arbeit nennt 45 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Acousto-optic sensing (AOS) is a non-contact method for measuring sound using light, suitable for environments where microphones are impractical, such as confined spaces or within airflow. Despite its effectiveness, AOS captures line-integrated sound pressure along the optical path, resulting in signals that cannot be interpreted as those from point-wise microphones. To obtain the sound pressure distribution in three-dimensional (3D) space, volumetric sound-field reconstruction is required. Existing methods require multi-directional line-integrated projection data, typically obtained either by deploying multiple devices or by repeatedly exciting the sound source. The former requires deploying multiple high-cost devices, which is often impractical, whereas the latter is not applicable to sound sources that cannot be reproduced consistently. To overcome these limitations, we propose a task called sound projection synthesis, which synthesizes data in specified directions based on observation data. We achieve this by using a latent diffusion model conditioned on observed projections and view angles to generate new sound-field projections. A model pretrained on natural images was fine-tuned using sound-field data and optimized with a pixel-wise loss. Experiments demonstrate that the model can generate realistic projection data. Combining nine observed views with nine generated views improved 3D reconstruction accuracy compared with using only nine observed views.

Autor:innen und Institutionen

  • Communication Science Laboratories, NTT, Inc., 3-1 Morinosato-Wakamiya, Atsugi, Kanagawa 243-0198, Japan.
  • Department of Intermedia Art and Science, Waseda University, 3-4-1 Ohkubo, Shinjuku-ku, Tokyo 169-8555, Japan.

ORCID-Profile: Risako Tanigawa, Kenji Ishikawa, Noboru Harada, Yasuhiro Oikawa

Zitieren

APA

Tanigawa, R., Ishikawa, K., Harada, N., & Oikawa, Y. (2026). Sound-field-projection synthesis using latent diffusion model for acousto-optic reconstruction. The Journal of the Acoustical Society of America, 159(5), 3858-3869. https://doi.org/10.1121/10.0043764

Vancouver

Tanigawa R, Ishikawa K, Harada N, Oikawa Y. Sound-field-projection synthesis using latent diffusion model for acousto-optic reconstruction. The Journal of the Acoustical Society of America. 2026;159(5):3858-3869. doi:10.1121/10.0043764

BibTeX
@article{Tanigawa2026,
  author = {Tanigawa, Risako and Ishikawa, Kenji and Harada, Noboru and Oikawa, Yasuhiro},
  title = {Sound-field-projection synthesis using latent diffusion model for acousto-optic reconstruction},
  journal = {The Journal of the Acoustical Society of America},
  year = {2026},
  volume = {159},
  number = {5},
  pages = {3858--3869},
  doi = {10.1121/10.0043764}
}
Kostenlos starten →