Unifying background models over complex audio using entropy

In this paper we extend an existing audio background modelling technique, leading to a more robust application to complex audio environments. The determination of background audio is used as an initial stage in the analysis of audio for surveillance and monitoring applications. Knowledge of the back...

Full description

Bibliographic Details
Main Authors: Moncrieff, Simon, Venkatesh, Svetha, West, Geoffrey
Other Authors: Tang, Y.
Format: Conference Paper
Published: IEEE Coputer Society Conference Publishing Services 2006
Online Access:http://hdl.handle.net/20.500.11937/42503
_version_ 1848756437555085312
author Moncrieff, Simon
Venkatesh, Svetha
West, Geoffrey
author2 Tang, Y.
author_facet Tang, Y.
Moncrieff, Simon
Venkatesh, Svetha
West, Geoffrey
author_sort Moncrieff, Simon
building Curtin Institutional Repository
collection Online Access
description In this paper we extend an existing audio background modelling technique, leading to a more robust application to complex audio environments. The determination of background audio is used as an initial stage in the analysis of audio for surveillance and monitoring applications. Knowledge of the background serves to highlight unusual or infrequent sounds. An existing modelling approach uses an online, adaptive Gaussian mixture model technique that uses multiple distributions to model variations in the background. The method used to determine the background distributions of the GMM leads to a failure mode of the existing technique when applied to complex audio. We propose a method incorporating further information, the proximity of distributions determined using entropy, to determine a more complete background model. The method was successful in more robustly modelling the background for complex audio scenes
first_indexed 2025-11-14T09:12:11Z
format Conference Paper
id curtin-20.500.11937-42503
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:12:11Z
publishDate 2006
publisher IEEE Coputer Society Conference Publishing Services
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-425032023-02-27T07:34:29Z Unifying background models over complex audio using entropy Moncrieff, Simon Venkatesh, Svetha West, Geoffrey Tang, Y. Wang, S. Lorette, G. Young, D. Yang, H. In this paper we extend an existing audio background modelling technique, leading to a more robust application to complex audio environments. The determination of background audio is used as an initial stage in the analysis of audio for surveillance and monitoring applications. Knowledge of the background serves to highlight unusual or infrequent sounds. An existing modelling approach uses an online, adaptive Gaussian mixture model technique that uses multiple distributions to model variations in the background. The method used to determine the background distributions of the GMM leads to a failure mode of the existing technique when applied to complex audio. We propose a method incorporating further information, the proximity of distributions determined using entropy, to determine a more complete background model. The method was successful in more robustly modelling the background for complex audio scenes 2006 Conference Paper http://hdl.handle.net/20.500.11937/42503 10.1109/ICPR.2006.1141 IEEE Coputer Society Conference Publishing Services fulltext
spellingShingle Moncrieff, Simon
Venkatesh, Svetha
West, Geoffrey
Unifying background models over complex audio using entropy
title Unifying background models over complex audio using entropy
title_full Unifying background models over complex audio using entropy
title_fullStr Unifying background models over complex audio using entropy
title_full_unstemmed Unifying background models over complex audio using entropy
title_short Unifying background models over complex audio using entropy
title_sort unifying background models over complex audio using entropy
url http://hdl.handle.net/20.500.11937/42503