Physics-Guided Variational Model for Unsupervised Sound Source Tracking

TL;DR

This paper presents an unsupervised, physics-guided variational model for sound source tracking that leverages geometric constraints and outperforms traditional methods without needing labeled data.

Contribution

It introduces a novel unsupervised model combining a variational encoder with a physics-based decoder for sound source tracking, capable of handling mismatched geometries and noise.

Findings

Outperforms traditional baselines in accuracy

Achieves comparable results to supervised models

Generalizes well to different array geometries

Abstract

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.