Real-time sensing and acoustic scene characterization for security applications

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Real-time acoustic scene analysis has several applications such as homeland security, surveillance, and monitoring. The development of a collaborative networking infrastructure can be valuable in scene analysis since feature parameters can be extracted locally (at the node level) and combined at the base station. In this context, distributed and agile wireless sensor networks (WSNs) have been of particular interest recently. In this paper, we propose real-time voice scene characterization algorithms for use in a wireless sensor network. Voice scene analysis is accomplished using a speech discriminator, a gender classifier, a system for recognizing the state of emotion, and an estimator of the number of speakers in an area of interest. Real-time implementations of these algorithms are accomplished using Crossbow motes and TI DSP boards, configured to operate in a wireless sensor network. A series of experiments are presented that characterize the performance of the algorithms under different conditions.

Original languageEnglish (US)
Title of host publication3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008, Proceedings
Pages755-758
Number of pages4
DOIs
StatePublished - 2008
Event3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008 - Santorini, Greece
Duration: May 7 2008May 9 2008

Other

Other3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008
CountryGreece
CitySantorini
Period5/7/085/9/08

Fingerprint

Wireless sensor networks
Acoustics
Discriminators
National security
Base stations
Classifiers
Monitoring
Experiments

Keywords

  • Acoustic scenes characterization
  • Real-time wireless sensor networks

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Cite this

Kwon, H., Berisha, V., & Spanias, A. (2008). Real-time sensing and acoustic scene characterization for security applications. In 3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008, Proceedings (pp. 755-758). [4556311] https://doi.org/10.1109/ISWPC.2008.4556311

Real-time sensing and acoustic scene characterization for security applications. / Kwon, Homin; Berisha, Visar; Spanias, Andreas.

3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008, Proceedings. 2008. p. 755-758 4556311.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kwon, H, Berisha, V & Spanias, A 2008, Real-time sensing and acoustic scene characterization for security applications. in 3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008, Proceedings., 4556311, pp. 755-758, 3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008, Santorini, Greece, 5/7/08. https://doi.org/10.1109/ISWPC.2008.4556311
Kwon H, Berisha V, Spanias A. Real-time sensing and acoustic scene characterization for security applications. In 3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008, Proceedings. 2008. p. 755-758. 4556311 https://doi.org/10.1109/ISWPC.2008.4556311
Kwon, Homin ; Berisha, Visar ; Spanias, Andreas. / Real-time sensing and acoustic scene characterization for security applications. 3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008, Proceedings. 2008. pp. 755-758
@inproceedings{90467edf5a2f46a8836fee0d61d1bc06,
title = "Real-time sensing and acoustic scene characterization for security applications",
abstract = "Real-time acoustic scene analysis has several applications such as homeland security, surveillance, and monitoring. The development of a collaborative networking infrastructure can be valuable in scene analysis since feature parameters can be extracted locally (at the node level) and combined at the base station. In this context, distributed and agile wireless sensor networks (WSNs) have been of particular interest recently. In this paper, we propose real-time voice scene characterization algorithms for use in a wireless sensor network. Voice scene analysis is accomplished using a speech discriminator, a gender classifier, a system for recognizing the state of emotion, and an estimator of the number of speakers in an area of interest. Real-time implementations of these algorithms are accomplished using Crossbow motes and TI DSP boards, configured to operate in a wireless sensor network. A series of experiments are presented that characterize the performance of the algorithms under different conditions.",
keywords = "Acoustic scenes characterization, Real-time wireless sensor networks",
author = "Homin Kwon and Visar Berisha and Andreas Spanias",
year = "2008",
doi = "10.1109/ISWPC.2008.4556311",
language = "English (US)",
isbn = "9781424416530",
pages = "755--758",
booktitle = "3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008, Proceedings",

}

TY - GEN

T1 - Real-time sensing and acoustic scene characterization for security applications

AU - Kwon, Homin

AU - Berisha, Visar

AU - Spanias, Andreas

PY - 2008

Y1 - 2008

N2 - Real-time acoustic scene analysis has several applications such as homeland security, surveillance, and monitoring. The development of a collaborative networking infrastructure can be valuable in scene analysis since feature parameters can be extracted locally (at the node level) and combined at the base station. In this context, distributed and agile wireless sensor networks (WSNs) have been of particular interest recently. In this paper, we propose real-time voice scene characterization algorithms for use in a wireless sensor network. Voice scene analysis is accomplished using a speech discriminator, a gender classifier, a system for recognizing the state of emotion, and an estimator of the number of speakers in an area of interest. Real-time implementations of these algorithms are accomplished using Crossbow motes and TI DSP boards, configured to operate in a wireless sensor network. A series of experiments are presented that characterize the performance of the algorithms under different conditions.

AB - Real-time acoustic scene analysis has several applications such as homeland security, surveillance, and monitoring. The development of a collaborative networking infrastructure can be valuable in scene analysis since feature parameters can be extracted locally (at the node level) and combined at the base station. In this context, distributed and agile wireless sensor networks (WSNs) have been of particular interest recently. In this paper, we propose real-time voice scene characterization algorithms for use in a wireless sensor network. Voice scene analysis is accomplished using a speech discriminator, a gender classifier, a system for recognizing the state of emotion, and an estimator of the number of speakers in an area of interest. Real-time implementations of these algorithms are accomplished using Crossbow motes and TI DSP boards, configured to operate in a wireless sensor network. A series of experiments are presented that characterize the performance of the algorithms under different conditions.

KW - Acoustic scenes characterization

KW - Real-time wireless sensor networks

UR - http://www.scopus.com/inward/record.url?scp=51649083540&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51649083540&partnerID=8YFLogxK

U2 - 10.1109/ISWPC.2008.4556311

DO - 10.1109/ISWPC.2008.4556311

M3 - Conference contribution

AN - SCOPUS:51649083540

SN - 9781424416530

SP - 755

EP - 758

BT - 3rd International Symposium on Wireless Pervasive Computing, ISWPC 2008, Proceedings

ER -