Sound Source Distance Estimation in Diverse and Dynamic Acoustic Conditions

TL;DR

This paper introduces a deep learning method for estimating the distance of moving sound sources in diverse acoustic environments, addressing a less-studied aspect of sound localization.

Contribution

It presents a CRNN model capable of estimating sound source distance across various datasets and environments, outperforming previous methods and analyzing optimal training strategies.

Findings

Model outperforms recent approaches in diverse environments

Inverse distance weighting loss improves accuracy

Deep learning enables robust distance estimation across conditions

Abstract

Localizing a moving sound source in the real world involves determining its direction-of-arrival (DOA) and distance relative to a microphone. Advancements in DOA estimation have been facilitated by data-driven methods optimized with large open-source datasets with microphone array recordings in diverse environments. In contrast, estimating a sound source's distance remains understudied. Existing approaches assume recordings by non-coincident microphones to use methods that are susceptible to differences in room reverberation. We present a CRNN able to estimate the distance of moving sound sources across multiple datasets featuring diverse rooms, outperforming a recently-published approach. We also characterize our model's performance as a function of sound source distance and different training losses. This analysis reveals optimal training using a loss that weighs model errors as an inverse function of the sound source true distance. Our study is the first to demonstrate that sound source distance estimation can be performed across diverse acoustic conditions using deep learning.