arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.08484eess.AS
收藏

物理引导的变分模型用于无监督声源跟踪

Physics-Guided Variational Model for Unsupervised Sound Source Tracking

Eindhoven University of Technology(埃因霍温理工大学);NXP Semiconductors(恩智浦半导体)

Luan Vinícius Fiorio, Ivana Nikoloska, Bruno Defraene, Alex Young, Johan David, Ronald M. Aarts

AI总结:

本文提出了一种物理引导的变分模型,用于无监督单源声源跟踪,通过几何约束和时间延迟似然性提升估计精度,实验表明其在准确性和效率上优于传统方法。

摘要:

声源跟踪通常使用经典阵列处理算法进行,而机器学习方法通常依赖于精确的声源位置标签,这些标签要么昂贵要么难以获取。本文介绍了一种物理引导的变分模型,能够实现完全无监督的单源声源跟踪。该方法结合了变分编码器和基于物理的解码器,通过解析推导出的成对时间延迟似然性将几何约束注入到潜在空间中。无需地面真实标签,模型能够直接从麦克风阵列信号中学习估计声源方向。在真实世界数据上的实验表明,所提出的方法优于传统基线,并且在准确性和计算复杂性方面与最先进的监督模型相当。我们进一步展示了该方法在不匹配的阵列几何结构中具有良好的泛化能力,并表现出对损坏的麦克风位置元数据的强鲁棒性。最后,我们概述了该方法扩展到多源跟踪的自然延伸,并提出了支持该扩展所需的理论修改。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑