Event Classification by Physics-informed Inpainting for Distributed Multichannel Acoustic Sensor with Partially Degraded Channels

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tonami, Noriyuki, Kohno, Wataru, Yajima, Yoshiyuki, Mishima, Sakiko, Arai, Yumi, Kondo, Reishi, Hino, Tomoyuki
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908775590395904
author Tonami, Noriyuki
Kohno, Wataru
Yajima, Yoshiyuki
Mishima, Sakiko
Arai, Yumi
Kondo, Reishi
Hino, Tomoyuki
author_facet Tonami, Noriyuki
Kohno, Wataru
Yajima, Yoshiyuki
Mishima, Sakiko
Arai, Yumi
Kondo, Reishi
Hino, Tomoyuki
contents Distributed multichannel acoustic sensing (DMAS) enables large-scale sound event classification (SEC), but performance drops when many channels are degraded and when sensor layouts at test time differ from training layouts. We propose a learning-free, physics-informed inpainting frontend based on reverse time migration (RTM). In this approach, observed multichannel spectrograms are first back-propagated on a 3D grid using an analytic Green's function to form a scene-consistent image, and then forward-projected to reconstruct inpainted signals before log-mel feature extraction and Transformer-based classification. We evaluate the method on ESC-50 with 50 sensors and three layouts (circular, linear, right-angle), where per-channel SNRs are sampled from -30 to 0 dB. Compared with an AST baseline, scaling-sparsemax channel selection, and channel-swap augmentation, the proposed RTM frontend achieves the best or competitive accuracy across all layouts, improving accuracy by 13.1 points on the right-angle layout (from 9.7% to 22.8%). Correlation analyses show that spatial weights align more strongly with SNR than with channel--source distance, and that higher SNR--weight correlation corresponds to higher SEC accuracy. These results demonstrate that a reconstruct-then-project, physics-based preprocessing effectively complements learning-only methods for DMAS under layout-open configurations and severe channel degradation.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13513
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Event Classification by Physics-informed Inpainting for Distributed Multichannel Acoustic Sensor with Partially Degraded Channels
Tonami, Noriyuki
Kohno, Wataru
Yajima, Yoshiyuki
Mishima, Sakiko
Arai, Yumi
Kondo, Reishi
Hino, Tomoyuki
Sound
Audio and Speech Processing
Distributed multichannel acoustic sensing (DMAS) enables large-scale sound event classification (SEC), but performance drops when many channels are degraded and when sensor layouts at test time differ from training layouts. We propose a learning-free, physics-informed inpainting frontend based on reverse time migration (RTM). In this approach, observed multichannel spectrograms are first back-propagated on a 3D grid using an analytic Green's function to form a scene-consistent image, and then forward-projected to reconstruct inpainted signals before log-mel feature extraction and Transformer-based classification. We evaluate the method on ESC-50 with 50 sensors and three layouts (circular, linear, right-angle), where per-channel SNRs are sampled from -30 to 0 dB. Compared with an AST baseline, scaling-sparsemax channel selection, and channel-swap augmentation, the proposed RTM frontend achieves the best or competitive accuracy across all layouts, improving accuracy by 13.1 points on the right-angle layout (from 9.7% to 22.8%). Correlation analyses show that spatial weights align more strongly with SNR than with channel--source distance, and that higher SNR--weight correlation corresponds to higher SEC accuracy. These results demonstrate that a reconstruct-then-project, physics-based preprocessing effectively complements learning-only methods for DMAS under layout-open configurations and severe channel degradation.
title Event Classification by Physics-informed Inpainting for Distributed Multichannel Acoustic Sensor with Partially Degraded Channels
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2601.13513