Graph neural networks for sound source localization on distributed microphone networks

TL;DR

This paper introduces a Graph Neural Network-based method for sound source localization on distributed microphone networks, effectively handling variable input channels and outperforming classical algorithms in experiments.

Contribution

The paper proposes a novel GNN-based localization method that adapts to varying microphone counts, bridging classical SSL algorithms with modern graph neural network techniques.

Findings

Outperforms classical SSL baselines in experiments

Handles variable number of microphones effectively

Uses Relation Network GNN for sound source localization

Abstract

Distributed Microphone Arrays (DMAs) present many challenges with respect to centralized microphone arrays. An important requirement of applications on these arrays is handling a variable number of input channels. We consider the use of Graph Neural Networks (GNNs) as a solution to this challenge. We present a localization method using the Relation Network GNN, which we show shares many similarities to classical signal processing algorithms for Sound Source Localization (SSL). We apply our method for the task of SSL and validate it experimentally using an unseen number of microphones. We test different feature extractors and show that our approach significantly outperforms classical baselines.