Adaptive speech enhancement with varying noise backgrounds

We present a new approach for speech enhancement in the presence of non-stationary and rapidly changing background noise. A distributed microphone system is used to capture the acoustic characteristics of the environment. The input of each microphone is then classified either as speech or one of the...

Full description

Bibliographic Details
Main Authors: Kϋhnapfel, Thorsten, Tan, Tele, Venkatesh, Svetha, Igel, B., Nordholm, Sven
Other Authors: Not known
Format: Conference Paper
Published: IEEE 2008
Online Access:http://hdl.handle.net/20.500.11937/28480
_version_ 1848752548691836928
author Kϋhnapfel, Thorsten
Tan, Tele
Venkatesh, Svetha
Igel, B.
Nordholm, Sven
author2 Not known
author_facet Not known
Kϋhnapfel, Thorsten
Tan, Tele
Venkatesh, Svetha
Igel, B.
Nordholm, Sven
author_sort Kϋhnapfel, Thorsten
building Curtin Institutional Repository
collection Online Access
description We present a new approach for speech enhancement in the presence of non-stationary and rapidly changing background noise. A distributed microphone system is used to capture the acoustic characteristics of the environment. The input of each microphone is then classified either as speech or one of the predetermined noise types. Further enhancement of speech in respective microphones is carried out using a modified spectral subtraction algorithm that incorporates multiple noise models to quickly adapt to rapid background noise changes. Tests on real world speech captured under diverse conditions demonstrate the effectiveness of this method.
first_indexed 2025-11-14T08:10:23Z
format Conference Paper
id curtin-20.500.11937-28480
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:10:23Z
publishDate 2008
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-284802018-03-29T09:09:14Z Adaptive speech enhancement with varying noise backgrounds Kϋhnapfel, Thorsten Tan, Tele Venkatesh, Svetha Igel, B. Nordholm, Sven Not known We present a new approach for speech enhancement in the presence of non-stationary and rapidly changing background noise. A distributed microphone system is used to capture the acoustic characteristics of the environment. The input of each microphone is then classified either as speech or one of the predetermined noise types. Further enhancement of speech in respective microphones is carried out using a modified spectral subtraction algorithm that incorporates multiple noise models to quickly adapt to rapid background noise changes. Tests on real world speech captured under diverse conditions demonstrate the effectiveness of this method. 2008 Conference Paper http://hdl.handle.net/20.500.11937/28480 10.1109/ICPR.2008.4761632 IEEE restricted
spellingShingle Kϋhnapfel, Thorsten
Tan, Tele
Venkatesh, Svetha
Igel, B.
Nordholm, Sven
Adaptive speech enhancement with varying noise backgrounds
title Adaptive speech enhancement with varying noise backgrounds
title_full Adaptive speech enhancement with varying noise backgrounds
title_fullStr Adaptive speech enhancement with varying noise backgrounds
title_full_unstemmed Adaptive speech enhancement with varying noise backgrounds
title_short Adaptive speech enhancement with varying noise backgrounds
title_sort adaptive speech enhancement with varying noise backgrounds
url http://hdl.handle.net/20.500.11937/28480