Physics-Guided Variational Model for Unsupervised Sound Source Tracking
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912897589837824 |
|---|---|
| author | Fiorio, Luan Vinícius Nikoloska, Ivana Defraene, Bruno Young, Alex David, Johan Aarts, Ronald M. |
| author_facet | Fiorio, Luan Vinícius Nikoloska, Ivana Defraene, Bruno Young, Alex David, Johan Aarts, Ronald M. |
| contents | Sound source tracking is commonly performed using classical array-processing algorithms, while machine-learning approaches typically rely on precise source position labels that are expensive or impractical to obtain. This paper introduces a physics-guided variational model capable of fully unsupervised single-source sound source tracking. The method combines a variational encoder with a physics-based decoder that injects geometric constraints into the latent space through analytically derived pairwise time-delay likelihoods. Without requiring ground-truth labels, the model learns to estimate source directions directly from microphone array signals. Experiments on real-world data demonstrate that the proposed approach outperforms traditional baselines and achieves accuracy and computational complexity comparable to state-of-the-art supervised models. We further show that the method generalizes well to mismatched array geometries and exhibits strong robustness to corrupted microphone position metadata. Finally, we outline a natural extension of the approach to multi-source tracking and present the theoretical modifications required to support it. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08484 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Physics-Guided Variational Model for Unsupervised Sound Source Tracking Fiorio, Luan Vinícius Nikoloska, Ivana Defraene, Bruno Young, Alex David, Johan Aarts, Ronald M. Audio and Speech Processing Sound source tracking is commonly performed using classical array-processing algorithms, while machine-learning approaches typically rely on precise source position labels that are expensive or impractical to obtain. This paper introduces a physics-guided variational model capable of fully unsupervised single-source sound source tracking. The method combines a variational encoder with a physics-based decoder that injects geometric constraints into the latent space through analytically derived pairwise time-delay likelihoods. Without requiring ground-truth labels, the model learns to estimate source directions directly from microphone array signals. Experiments on real-world data demonstrate that the proposed approach outperforms traditional baselines and achieves accuracy and computational complexity comparable to state-of-the-art supervised models. We further show that the method generalizes well to mismatched array geometries and exhibits strong robustness to corrupted microphone position metadata. Finally, we outline a natural extension of the approach to multi-source tracking and present the theoretical modifications required to support it. |
| title | Physics-Guided Variational Model for Unsupervised Sound Source Tracking |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2602.08484 |