English

Reconstruction of Sound Field through Diffusion Models

Audio and Speech Processing 2024-02-22 v2 Machine Learning Sound Signal Processing

Abstract

Reconstructing the sound field in a room is an important task for several applications, such as sound control and augmented (AR) or virtual reality (VR). In this paper, we propose a data-driven generative model for reconstructing the magnitude of acoustic fields in rooms with a focus on the modal frequency range. We introduce, for the first time, the use of a conditional Denoising Diffusion Probabilistic Model (DDPM) trained in order to reconstruct the sound field (SF-Diff) over an extended domain. The architecture is devised in order to be conditioned on a set of limited available measurements at different frequencies and generate the sound field in target, unknown, locations. The results show that SF-Diff is able to provide accurate reconstructions, outperforming a state-of-the-art baseline based on kernel interpolation.

Keywords

Cite

@article{arxiv.2312.08821,
  title  = {Reconstruction of Sound Field through Diffusion Models},
  author = {Federico Miotello and Luca Comanducci and Mirco Pezzoli and Alberto Bernardini and Fabio Antonacci and Augusto Sarti},
  journal= {arXiv preprint arXiv:2312.08821},
  year   = {2024}
}

Comments

Accepted for publication at ICASSP 2024

R2 v1 2026-06-28T13:50:44.264Z