Beamspace blind signal separation for speech enhancement

Signal processing methods for speech enhancement are of vital interest for communications equipments. In particular, multichannel algorithms, which perform spatial filtering to separate signals that have overlapping frequency content but different spatial origins, are important for a wide range of a...

Full description

Bibliographic Details
Main Authors: Low, Siow, Yiu, Ka Fai, Nordholm, Sven
Format: Journal Article
Published: Springer Netherlands 2009
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/33312
_version_ 1848753911145431040
author Low, Siow
Yiu, Ka Fai
Nordholm, Sven
author_facet Low, Siow
Yiu, Ka Fai
Nordholm, Sven
author_sort Low, Siow
building Curtin Institutional Repository
collection Online Access
description Signal processing methods for speech enhancement are of vital interest for communications equipments. In particular, multichannel algorithms, which perform spatial filtering to separate signals that have overlapping frequency content but different spatial origins, are important for a wide range of applications. Two of the most popular multichannel methods are blind signal separation (BSS) and beamforming. Briefly, (BSS) separates mixed sources by optimizing the statistical independence among the outputs whilst beamforming optimizes the look direction of the desired source(s). However, both methods have separation limitations, in that BSS succumbs to reverberant environments and beamforming is very sensitive to array model mismatch. In this paper, we propose a novel hybrid scheme, called beamspace BSS, which is intended to compensate the aforementioned separation weaknesses by jointly optimizing the spatial selectivity and statistical independence of the sources. We show that beamspace BSS outperforms the separation performance of the conventional sensor space BSS significantly, particularly in reverberant room environments.
first_indexed 2025-11-14T08:32:02Z
format Journal Article
id curtin-20.500.11937-33312
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:32:02Z
publishDate 2009
publisher Springer Netherlands
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-333122017-09-13T16:07:33Z Beamspace blind signal separation for speech enhancement Low, Siow Yiu, Ka Fai Nordholm, Sven Speech enhancement Blind signal separation Microphone arrays Beamspace Signal processing methods for speech enhancement are of vital interest for communications equipments. In particular, multichannel algorithms, which perform spatial filtering to separate signals that have overlapping frequency content but different spatial origins, are important for a wide range of applications. Two of the most popular multichannel methods are blind signal separation (BSS) and beamforming. Briefly, (BSS) separates mixed sources by optimizing the statistical independence among the outputs whilst beamforming optimizes the look direction of the desired source(s). However, both methods have separation limitations, in that BSS succumbs to reverberant environments and beamforming is very sensitive to array model mismatch. In this paper, we propose a novel hybrid scheme, called beamspace BSS, which is intended to compensate the aforementioned separation weaknesses by jointly optimizing the spatial selectivity and statistical independence of the sources. We show that beamspace BSS outperforms the separation performance of the conventional sensor space BSS significantly, particularly in reverberant room environments. 2009 Journal Article http://hdl.handle.net/20.500.11937/33312 10.1007/s11081-008-9060-4 Springer Netherlands fulltext
spellingShingle Speech enhancement
Blind signal separation
Microphone arrays
Beamspace
Low, Siow
Yiu, Ka Fai
Nordholm, Sven
Beamspace blind signal separation for speech enhancement
title Beamspace blind signal separation for speech enhancement
title_full Beamspace blind signal separation for speech enhancement
title_fullStr Beamspace blind signal separation for speech enhancement
title_full_unstemmed Beamspace blind signal separation for speech enhancement
title_short Beamspace blind signal separation for speech enhancement
title_sort beamspace blind signal separation for speech enhancement
topic Speech enhancement
Blind signal separation
Microphone arrays
Beamspace
url http://hdl.handle.net/20.500.11937/33312