Sound Source Localization for Human-Robot Interaction in Outdoor Environments

TL;DR

This paper introduces a sound source localization method for outdoor human-robot interaction using microphone arrays and advanced signal processing, achieving high accuracy in noisy environments.

Contribution

It combines a coarse alignment with a time-domain echo cancellation and ideal ratio mask estimation, advancing outdoor sound localization capabilities.

Findings

Average angle error of 4 degrees

95% accuracy within 5 degrees at 1dB SNR

Significantly outperforms existing methods

Abstract

This paper presents a sound source localization strategy that relies on a microphone array embedded in an unmanned ground vehicle and an asynchronous close-talking microphone near the operator. A signal coarse alignment strategy is combined with a time-domain acoustic echo cancellation algorithm to estimate a time-frequency ideal ratio mask to isolate the target speech from interferences and environmental noise. This allows selective sound source localization, and provides the robot with the direction of arrival of sound from the active operator, which enables rich interaction in noisy scenarios. Results demonstrate an average angle error of 4 degrees and an accuracy within 5 degrees of 95\% at a signal-to-noise ratio of 1dB, which is significantly superior to the state-of-the-art localization methods.