Robust Source Localization in Reverberant Environments Based on Weighted Fuzzy Clustering

Successful localization of sound sources in reverberant enclosures is an important prerequisite for many spatial signal processing algorithms. We investigate the use of a weighted fuzzy-means cluster algorithm for robust source localization using location cues extracted from a microphone array. In o...

Full description

Bibliographic Details
Main Authors: Kuhne, M., Togneri, R., Nordholm, Sven
Format: Journal Article
Published: IEEE Signal Processing Society 2009
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/36103
_version_ 1848754676379418624
author Kuhne, M.
Togneri, R.
Nordholm, Sven
author_facet Kuhne, M.
Togneri, R.
Nordholm, Sven
author_sort Kuhne, M.
building Curtin Institutional Repository
collection Online Access
description Successful localization of sound sources in reverberant enclosures is an important prerequisite for many spatial signal processing algorithms. We investigate the use of a weighted fuzzy-means cluster algorithm for robust source localization using location cues extracted from a microphone array. In orderto increase the algorithm's robustness against sound reflections, we incorporate observation weights to emphasize reliable cues over unreliable ones. The weights are computed from local feature statistics around sound onsets because it is known that these regions are least affected by reverberation. Experimental results illustrate the superiority of the method when compared with standard fuzzy clustering. The proposed algorithm successfully located two speech sources for a range of angular separations in room environments with reverberation times of up to 600 ms.
first_indexed 2025-11-14T08:44:12Z
format Journal Article
id curtin-20.500.11937-36103
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:44:12Z
publishDate 2009
publisher IEEE Signal Processing Society
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-361032017-01-30T13:53:40Z Robust Source Localization in Reverberant Environments Based on Weighted Fuzzy Clustering Kuhne, M. Togneri, R. Nordholm, Sven microphone array Fuzzy clustering - source localization reverberation Successful localization of sound sources in reverberant enclosures is an important prerequisite for many spatial signal processing algorithms. We investigate the use of a weighted fuzzy-means cluster algorithm for robust source localization using location cues extracted from a microphone array. In orderto increase the algorithm's robustness against sound reflections, we incorporate observation weights to emphasize reliable cues over unreliable ones. The weights are computed from local feature statistics around sound onsets because it is known that these regions are least affected by reverberation. Experimental results illustrate the superiority of the method when compared with standard fuzzy clustering. The proposed algorithm successfully located two speech sources for a range of angular separations in room environments with reverberation times of up to 600 ms. 2009 Journal Article http://hdl.handle.net/20.500.11937/36103 IEEE Signal Processing Society fulltext
spellingShingle microphone array
Fuzzy clustering
- source localization
reverberation
Kuhne, M.
Togneri, R.
Nordholm, Sven
Robust Source Localization in Reverberant Environments Based on Weighted Fuzzy Clustering
title Robust Source Localization in Reverberant Environments Based on Weighted Fuzzy Clustering
title_full Robust Source Localization in Reverberant Environments Based on Weighted Fuzzy Clustering
title_fullStr Robust Source Localization in Reverberant Environments Based on Weighted Fuzzy Clustering
title_full_unstemmed Robust Source Localization in Reverberant Environments Based on Weighted Fuzzy Clustering
title_short Robust Source Localization in Reverberant Environments Based on Weighted Fuzzy Clustering
title_sort robust source localization in reverberant environments based on weighted fuzzy clustering
topic microphone array
Fuzzy clustering
- source localization
reverberation
url http://hdl.handle.net/20.500.11937/36103