A robust approach to reverberant blind source separation in the presence of noise for arbitrarily arranged sensors

Considerable attention has been devoted to the reverberant blind source separation problem: in particular, the concept of time-frequency masking. However, realistic acoustic scenarios often comprise not only reverberation, but also additive noise due to factors such as non-ideal channels. This paper...

Full description

Bibliographic Details
Main Authors: Jafari, I., Togneri, R., Nordholm, Sven
Other Authors: Akihiko Sugiyama
Format: Conference Paper
Published: The Institute of Electrical and Electronics Engineers 2012
Online Access:http://hdl.handle.net/20.500.11937/18549
_version_ 1848749775905619968
author Jafari, I.
Togneri, R.
Nordholm, Sven
author2 Akihiko Sugiyama
author_facet Akihiko Sugiyama
Jafari, I.
Togneri, R.
Nordholm, Sven
author_sort Jafari, I.
building Curtin Institutional Repository
collection Online Access
description Considerable attention has been devoted to the reverberant blind source separation problem: in particular, the concept of time-frequency masking. However, realistic acoustic scenarios often comprise not only reverberation, but also additive noise due to factors such as non-ideal channels. This paper presents robust evaluations of a time-frequency masking approach for separation in such realistic conditions. The fuzzy c-means clustering algorithm is used to cluster spatial feature cues into a time-frequency mask. Experimental results demonstrated superiority in separation, with notable improvements in the SNR additionally observed. Not only does this establish the proposed scheme viable for reverberant blind source separation, but also as a credible means of speech enhancement in the presence of additive broadband noise.
first_indexed 2025-11-14T07:26:18Z
format Conference Paper
id curtin-20.500.11937-18549
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:26:18Z
publishDate 2012
publisher The Institute of Electrical and Electronics Engineers
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-185492023-02-02T07:57:39Z A robust approach to reverberant blind source separation in the presence of noise for arbitrarily arranged sensors Jafari, I. Togneri, R. Nordholm, Sven Akihiko Sugiyama Hitoshi Kiya Considerable attention has been devoted to the reverberant blind source separation problem: in particular, the concept of time-frequency masking. However, realistic acoustic scenarios often comprise not only reverberation, but also additive noise due to factors such as non-ideal channels. This paper presents robust evaluations of a time-frequency masking approach for separation in such realistic conditions. The fuzzy c-means clustering algorithm is used to cluster spatial feature cues into a time-frequency mask. Experimental results demonstrated superiority in separation, with notable improvements in the SNR additionally observed. Not only does this establish the proposed scheme viable for reverberant blind source separation, but also as a credible means of speech enhancement in the presence of additive broadband noise. 2012 Conference Paper http://hdl.handle.net/20.500.11937/18549 10.1109/ICASSP.2012.6288402 The Institute of Electrical and Electronics Engineers restricted
spellingShingle Jafari, I.
Togneri, R.
Nordholm, Sven
A robust approach to reverberant blind source separation in the presence of noise for arbitrarily arranged sensors
title A robust approach to reverberant blind source separation in the presence of noise for arbitrarily arranged sensors
title_full A robust approach to reverberant blind source separation in the presence of noise for arbitrarily arranged sensors
title_fullStr A robust approach to reverberant blind source separation in the presence of noise for arbitrarily arranged sensors
title_full_unstemmed A robust approach to reverberant blind source separation in the presence of noise for arbitrarily arranged sensors
title_short A robust approach to reverberant blind source separation in the presence of noise for arbitrarily arranged sensors
title_sort robust approach to reverberant blind source separation in the presence of noise for arbitrarily arranged sensors
url http://hdl.handle.net/20.500.11937/18549