A dual-branch fusion network for footstep sound source localization in non-line-of-sight corridors
The Journal of the Acoustical Society of America · 01.08.2026 · 160 (2) · 1400-1412
DOI: 10.1121/10.0044386 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 11.08.2026. Verfasst von Xiaonan Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Communication Engineering, Dalian University of Technology, Dalian 116024, China. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Natural Science Foundations of China, National High Technology Research and Development Programof China, Natural Science Foundation of Liaoning Province of China.
Abstract (Originalsprache)
Non-line-of-sight (NLOS) acoustic source localization using microphone arrays has attracted increasing attention in robotics due to its non-intrusive nature, low cost, and ease of integration. However, existing methods typically rely on accurate environmental models and ideal propagation assumptions, resulting in limited robustness in complex multipath environments. To address these issues, this paper proposes CorridorLocNet, a dual-branch fusion network for footstep sound source localization in NLOS corridors. Specifically, Mel-spectrogram and generalized cross correlation with phase transform features are first concatenated into a joint input. Subsequently, a dual-branch architecture is proposed, comprising a residual convolutional branch to extract local time-frequency patterns and a lightweight Conformer branch to capture global temporal dependencies. Furthermore, a cross-attention module adaptively fuses high-dimensional representations from both branches. Finally, a multi-layer perceptron outputs the estimated position. By learning the complex mapping from spatial sound field variations to source positions, the proposed method provides a robust solution in NLOS corridors. Additionally, a real-world dataset of footsteps occurring behind a corridor corner is constructed for evaluation. Experimental results demonstrate that CorridorLocNet achieves 98.83% classification accuracy and reduces the average error by 2.56 m compared with the reflection-aware localization approach, validating its feasibility in NLOS localization scenarios.
Autor:innen und Institutionen
- School of Information and Communication Engineering, Dalian University of Technology, Dalian 116024, China.
ORCID-Profile: Xiaonan Wang, Zhe Chen, Fuliang Yin
Förderung
- Natural Science Foundations of China
- National High Technology Research and Development Programof China
- Natural Science Foundation of Liaoning Province of China
- Fundamental Research Fund for the Central Universities of China
Zitieren
APA
Wang, X., Chen, Z., & Yin, F. (2026). A dual-branch fusion network for footstep sound source localization in non-line-of-sight corridors. The Journal of the Acoustical Society of America, 160(2), 1400-1412. https://doi.org/10.1121/10.0044386
Vancouver
Wang X, Chen Z, Yin F. A dual-branch fusion network for footstep sound source localization in non-line-of-sight corridors. The Journal of the Acoustical Society of America. 2026;160(2):1400-1412. doi:10.1121/10.0044386
BibTeX
@article{Wang2026,
author = {Wang, Xiaonan and Chen, Zhe and Yin, Fuliang},
title = {A dual-branch fusion network for footstep sound source localization in non-line-of-sight corridors},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
volume = {160},
number = {2},
pages = {1400--1412},
doi = {10.1121/10.0044386}
}
EUVIMED