Sound Source Localization for Human-Robot Interaction in Outdoor Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Victor, Du, Timothy, Sehn, Jordy, Collier, Jack, Grondin, François
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918106951057408
author Liu, Victor
Du, Timothy
Sehn, Jordy
Collier, Jack
Grondin, François
author_facet Liu, Victor
Du, Timothy
Sehn, Jordy
Collier, Jack
Grondin, François
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21431
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sound Source Localization for Human-Robot Interaction in Outdoor Environments
Liu, Victor
Du, Timothy
Sehn, Jordy
Collier, Jack
Grondin, François
Robotics
Human-Computer Interaction
Audio and Speech Processing
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.
title Sound Source Localization for Human-Robot Interaction in Outdoor Environments
topic Robotics
Human-Computer Interaction
Audio and Speech Processing
url https://arxiv.org/abs/2507.21431