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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Di Carlo, Diego, Fontaine, Mathieu, Nugraha, Aditya Arie, Bando, Yoshiaki, Yoshii, Kazuyoshi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908418612133888
author Di Carlo, Diego
Fontaine, Mathieu
Nugraha, Aditya Arie
Bando, Yoshiaki
Yoshii, Kazuyoshi
author_facet Di Carlo, Diego
Fontaine, Mathieu
Nugraha, Aditya Arie
Bando, Yoshiaki
Yoshii, Kazuyoshi
contents This paper describes a sound source localization (SSL) technique that combines an $α$-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 $α$-stable spatial measure, which represents the most plausible direction of arrival (DOA) of a target signal. As an $α$-stable model for the non-Gaussian case ($α$ $\in$ (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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18954
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SHAMaNS: Sound Localization with Hybrid Alpha-Stable Spatial Measure and Neural Steerer
Di Carlo, Diego
Fontaine, Mathieu
Nugraha, Aditya Arie
Bando, Yoshiaki
Yoshii, Kazuyoshi
Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
This paper describes a sound source localization (SSL) technique that combines an $α$-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 $α$-stable spatial measure, which represents the most plausible direction of arrival (DOA) of a target signal. As an $α$-stable model for the non-Gaussian case ($α$ $\in$ (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.
title SHAMaNS: Sound Localization with Hybrid Alpha-Stable Spatial Measure and Neural Steerer
topic Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2506.18954