Acoustic Speaker Localization with Strong Reverberation and Adaptive Feature Filtering with a Bayes RFS Framework

The thesis investigates the challenges of speaker localization in presence of strong reverberation, multi-speaker tracking, and multi-feature multi-speaker state filtering, using sound recordings from microphones. Novel reverberation-robust speaker localization algorithms are derived from the signal...

Full description

Bibliographic Details
Main Author: Lin, Shoufeng
Format: Thesis
Published: Curtin University 2019
Online Access:http://hdl.handle.net/20.500.11937/76069
_version_ 1848763624937488384
author Lin, Shoufeng
author_facet Lin, Shoufeng
author_sort Lin, Shoufeng
building Curtin Institutional Repository
collection Online Access
description The thesis investigates the challenges of speaker localization in presence of strong reverberation, multi-speaker tracking, and multi-feature multi-speaker state filtering, using sound recordings from microphones. Novel reverberation-robust speaker localization algorithms are derived from the signal and room acoustics models. A multi-speaker tracking filter and a multi-feature multi-speaker state filter are developed based upon the generalized labeled multi-Bernoulli random finite set framework. Experiments and comparative studies have verified and demonstrated the benefits of the proposed methods.
first_indexed 2025-11-14T11:06:26Z
format Thesis
id curtin-20.500.11937-76069
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:06:26Z
publishDate 2019
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-760692021-08-17T02:42:10Z Acoustic Speaker Localization with Strong Reverberation and Adaptive Feature Filtering with a Bayes RFS Framework Lin, Shoufeng The thesis investigates the challenges of speaker localization in presence of strong reverberation, multi-speaker tracking, and multi-feature multi-speaker state filtering, using sound recordings from microphones. Novel reverberation-robust speaker localization algorithms are derived from the signal and room acoustics models. A multi-speaker tracking filter and a multi-feature multi-speaker state filter are developed based upon the generalized labeled multi-Bernoulli random finite set framework. Experiments and comparative studies have verified and demonstrated the benefits of the proposed methods. 2019 Thesis http://hdl.handle.net/20.500.11937/76069 Curtin University fulltext
spellingShingle Lin, Shoufeng
Acoustic Speaker Localization with Strong Reverberation and Adaptive Feature Filtering with a Bayes RFS Framework
title Acoustic Speaker Localization with Strong Reverberation and Adaptive Feature Filtering with a Bayes RFS Framework
title_full Acoustic Speaker Localization with Strong Reverberation and Adaptive Feature Filtering with a Bayes RFS Framework
title_fullStr Acoustic Speaker Localization with Strong Reverberation and Adaptive Feature Filtering with a Bayes RFS Framework
title_full_unstemmed Acoustic Speaker Localization with Strong Reverberation and Adaptive Feature Filtering with a Bayes RFS Framework
title_short Acoustic Speaker Localization with Strong Reverberation and Adaptive Feature Filtering with a Bayes RFS Framework
title_sort acoustic speaker localization with strong reverberation and adaptive feature filtering with a bayes rfs framework
url http://hdl.handle.net/20.500.11937/76069