Indoor Sound Source Localization with Probabilistic Neural Network

TL;DR

This paper introduces a probabilistic neural network-based algorithm called GCA for indoor sound source localization, demonstrating high accuracy and robustness in challenging environments with high reverberation and noise.

Contribution

The paper presents a novel GCA algorithm that improves localization accuracy and robustness in adverse indoor acoustic conditions compared to existing methods.

Findings

GCA achieves average azimuth and elevation errors of 4.6° and 3.1°.

GCA significantly increases success rate in direction of arrival estimation.

GCA maintains robustness across diverse indoor environments.

Abstract

It is known that adverse environments such as high reverberation and low signal-to-noise ratio (SNR) pose a great challenge to indoor sound source localization. To address this challenge, in this paper, we propose a sound source localization algorithm based on probabilistic neural network, namely Generalized cross correlation Classification Algorithm (GCA). Experimental results for adverse environments with high reverberation time T60 up to 600ms and low SNR such as -10dB show that, the average azimuth angle error and elevation angle error by GCA are only 4.6 degrees and 3.1 degrees respectively. Compared with three recently published algorithms, GCA has increased the success rate on direction of arrival estimation significantly with good robustness to environmental changes. These results show that the proposed GCA can localize accurately and robustly for diverse indoor applications where the site acoustic features can be studied prior to the localization stage.