SHAMaNS: Sound Localization with Hybrid Alpha-Stable Spatial Measure and Neural Steerer

TL;DR

SHAMaNS introduces a hybrid sound source localization method combining alpha-stable spatial modeling with neural network-based steering vector interpolation, improving accuracy in multi-source scenarios.

Contribution

The paper presents a novel SSL approach that integrates an alpha-stable spatial measure with a physics-informed neural network for steering vector interpolation, enhancing robustness.

Findings

Outperforms state-of-the-art SSL methods in multi-source environments.

Leverages alpha-stable models to handle non-Gaussian noise.

Uses neural networks to interpolate steering vectors for better DOA estimation.

Abstract

This paper describes a sound source localization (SSL) technique that combines an $\alpha$-stable model for the observed signal with a neural network-based approach for modeling steering vectors. Specifically, a physics-informed neural network, referred to as Neural Steerer, is used to interpolate measured steering vectors (SVs) on a fixed microphone array. This allows for a more robust estimation of the so-called $\alpha$-stable spatial measure, which represents the most plausible direction of arrival (DOA) of a target signal. As an $\alpha$-stable model for the non-Gaussian case ($\alpha$ $\in$ (0, 2)) theoretically defines a unique spatial measure, we choose to leverage it to account for residual reconstruction error of the Neural Steerer in the downstream tasks. The objective scores indicate that our proposed technique outperforms state-of-the-art methods in the case of multiple sound sources.