Multiple moving speaker tracking via degenerate unmixing estimation technique and Cardinality Balanced Multi-target Multi-Bernoulli Filter (DUET-CBMeMBer)

The "cocktail party problem" has always been a challenging problem to solve and many blind source separation algorithms have been proposed as solutions. This problem has mainly been discussed for non-moving sound sources but it still remains for moving sound sources and high acoustic rever...

Full description

Bibliographic Details
Main Authors: Chong, N., Wong, S., Vo, Ba Tuong, Nordholm, Sven, Murray, Iain
Other Authors: Winston Seah
Format: Conference Paper
Published: IEEE 2014
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/24543
_version_ 1848751460243734528
author Chong, N.
Wong, S.
Vo, Ba Tuong
Nordholm, Sven
Murray, Iain
author2 Winston Seah
author_facet Winston Seah
Chong, N.
Wong, S.
Vo, Ba Tuong
Nordholm, Sven
Murray, Iain
author_sort Chong, N.
building Curtin Institutional Repository
collection Online Access
description The "cocktail party problem" has always been a challenging problem to solve and many blind source separation algorithms have been proposed as solutions. This problem has mainly been discussed for non-moving sound sources but it still remains for moving sound sources and high acoustic reverberations. The ability to localise and track multiple moving speakers is a pre-requisite to solving this problem. The aim of this paper is to show that a combination of Degenerate Unmixing Estimation Technique and a Cardinality Balanced Multitarget Multi-Bernoulli Filter provides a viable way to track multiple sound sources and subsequently address the problem of sound separation for moving targets.
first_indexed 2025-11-14T07:53:04Z
format Conference Paper
id curtin-20.500.11937-24543
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:53:04Z
publishDate 2014
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-245432023-02-27T07:34:30Z Multiple moving speaker tracking via degenerate unmixing estimation technique and Cardinality Balanced Multi-target Multi-Bernoulli Filter (DUET-CBMeMBer) Chong, N. Wong, S. Vo, Ba Tuong Nordholm, Sven Murray, Iain Winston Seah Stephane Maag Jayavardhana Gubbi Blind Source Separation sound localisation DUET CBMeMBer filter multiple speaker tracking The "cocktail party problem" has always been a challenging problem to solve and many blind source separation algorithms have been proposed as solutions. This problem has mainly been discussed for non-moving sound sources but it still remains for moving sound sources and high acoustic reverberations. The ability to localise and track multiple moving speakers is a pre-requisite to solving this problem. The aim of this paper is to show that a combination of Degenerate Unmixing Estimation Technique and a Cardinality Balanced Multitarget Multi-Bernoulli Filter provides a viable way to track multiple sound sources and subsequently address the problem of sound separation for moving targets. 2014 Conference Paper http://hdl.handle.net/20.500.11937/24543 10.1109/ISSNIP.2014.6827608 IEEE restricted
spellingShingle Blind Source Separation
sound localisation
DUET
CBMeMBer filter
multiple speaker tracking
Chong, N.
Wong, S.
Vo, Ba Tuong
Nordholm, Sven
Murray, Iain
Multiple moving speaker tracking via degenerate unmixing estimation technique and Cardinality Balanced Multi-target Multi-Bernoulli Filter (DUET-CBMeMBer)
title Multiple moving speaker tracking via degenerate unmixing estimation technique and Cardinality Balanced Multi-target Multi-Bernoulli Filter (DUET-CBMeMBer)
title_full Multiple moving speaker tracking via degenerate unmixing estimation technique and Cardinality Balanced Multi-target Multi-Bernoulli Filter (DUET-CBMeMBer)
title_fullStr Multiple moving speaker tracking via degenerate unmixing estimation technique and Cardinality Balanced Multi-target Multi-Bernoulli Filter (DUET-CBMeMBer)
title_full_unstemmed Multiple moving speaker tracking via degenerate unmixing estimation technique and Cardinality Balanced Multi-target Multi-Bernoulli Filter (DUET-CBMeMBer)
title_short Multiple moving speaker tracking via degenerate unmixing estimation technique and Cardinality Balanced Multi-target Multi-Bernoulli Filter (DUET-CBMeMBer)
title_sort multiple moving speaker tracking via degenerate unmixing estimation technique and cardinality balanced multi-target multi-bernoulli filter (duet-cbmember)
topic Blind Source Separation
sound localisation
DUET
CBMeMBer filter
multiple speaker tracking
url http://hdl.handle.net/20.500.11937/24543