Single-Microphone-Based Sound Source Localization for Mobile Robots in Reverberant Environments

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Jiang, Shi, Runwu, Yen, Benjamin, Kong, He, Nakadai, Kazuhiro
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913901541588992
author Wang, Jiang
Shi, Runwu
Yen, Benjamin
Kong, He
Nakadai, Kazuhiro
author_facet Wang, Jiang
Shi, Runwu
Yen, Benjamin
Kong, He
Nakadai, Kazuhiro
contents Accurately estimating sound source positions is crucial for robot audition. However, existing sound source localization methods typically rely on a microphone array with at least two spatially preconfigured microphones. This requirement hinders the applicability of microphone-based robot audition systems and technologies. To alleviate these challenges, we propose an online sound source localization method that uses a single microphone mounted on a mobile robot in reverberant environments. Specifically, we develop a lightweight neural network model with only 43k parameters to perform real-time distance estimation by extracting temporal information from reverberant signals. The estimated distances are then processed using an extended Kalman filter to achieve online sound source localization. To the best of our knowledge, this is the first work to achieve online sound source localization using a single microphone on a moving robot, a gap that we aim to fill in this work. Extensive experiments demonstrate the effectiveness and merits of our approach. To benefit the broader research community, we have open-sourced our code at https://github.com/JiangWAV/single-mic-SSL.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16173
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Single-Microphone-Based Sound Source Localization for Mobile Robots in Reverberant Environments
Wang, Jiang
Shi, Runwu
Yen, Benjamin
Kong, He
Nakadai, Kazuhiro
Robotics
Sound
Audio and Speech Processing
Accurately estimating sound source positions is crucial for robot audition. However, existing sound source localization methods typically rely on a microphone array with at least two spatially preconfigured microphones. This requirement hinders the applicability of microphone-based robot audition systems and technologies. To alleviate these challenges, we propose an online sound source localization method that uses a single microphone mounted on a mobile robot in reverberant environments. Specifically, we develop a lightweight neural network model with only 43k parameters to perform real-time distance estimation by extracting temporal information from reverberant signals. The estimated distances are then processed using an extended Kalman filter to achieve online sound source localization. To the best of our knowledge, this is the first work to achieve online sound source localization using a single microphone on a moving robot, a gap that we aim to fill in this work. Extensive experiments demonstrate the effectiveness and merits of our approach. To benefit the broader research community, we have open-sourced our code at https://github.com/JiangWAV/single-mic-SSL.
title Single-Microphone-Based Sound Source Localization for Mobile Robots in Reverberant Environments
topic Robotics
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2506.16173