A sensor network for real-time acoustic scene analysis

Homin Kwon, Harish Krishnamoorthi, Visar Berisha, Andreas Spanias

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

9 Citations (Scopus)

Abstract

Acoustic scene analysis can be used to extract relevant information in applications such as homeland security, surveillance and environmental monitoring. Wireless sensor networks have been of particular interest in monitoring acoustic scenes. Sensors embedded in such a network typically operate under several constraints such as low power and limited bandwidth. In this paper, we consider resource-efficient acoustic sensing tasks that extract and transmit relevant information to a central station where information assessment can be conducted. We propose a series of acoustic scene analysis tasks that are performed in a hierarchical manner. Hierarchical tasks include sound and speech discrimination, estimation of the number of speakers from the acquired sound, gender and emotional state, and ultimately voice monitoring and key word spotting. We apply support vector machine and Gaussian mixture model algorithms on sound features. A real-time implementation is accomplished using Crossbow motes interfaced with a TI DSP board. A series of experiments are presented to characterize the performance of the algorithms under different conditions.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Symposium on Circuits and Systems
Pages169-172
Number of pages4
DOIs
StatePublished - 2009
Event2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009 - Taipei, Taiwan, Province of China
Duration: May 24 2009May 27 2009

Other

Other2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009
CountryTaiwan, Province of China
CityTaipei
Period5/24/095/27/09

Fingerprint

Sensor networks
Acoustics
Acoustic waves
Monitoring
National security
Support vector machines
Wireless sensor networks
Bandwidth
Sensors
Experiments

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Kwon, H., Krishnamoorthi, H., Berisha, V., & Spanias, A. (2009). A sensor network for real-time acoustic scene analysis. In Proceedings - IEEE International Symposium on Circuits and Systems (pp. 169-172). [5117712] https://doi.org/10.1109/ISCAS.2009.5117712

A sensor network for real-time acoustic scene analysis. / Kwon, Homin; Krishnamoorthi, Harish; Berisha, Visar; Spanias, Andreas.

Proceedings - IEEE International Symposium on Circuits and Systems. 2009. p. 169-172 5117712.

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

Kwon, H, Krishnamoorthi, H, Berisha, V & Spanias, A 2009, A sensor network for real-time acoustic scene analysis. in Proceedings - IEEE International Symposium on Circuits and Systems., 5117712, pp. 169-172, 2009 IEEE International Symposium on Circuits and Systems, ISCAS 2009, Taipei, Taiwan, Province of China, 5/24/09. https://doi.org/10.1109/ISCAS.2009.5117712
Kwon H, Krishnamoorthi H, Berisha V, Spanias A. A sensor network for real-time acoustic scene analysis. In Proceedings - IEEE International Symposium on Circuits and Systems. 2009. p. 169-172. 5117712 https://doi.org/10.1109/ISCAS.2009.5117712
Kwon, Homin ; Krishnamoorthi, Harish ; Berisha, Visar ; Spanias, Andreas. / A sensor network for real-time acoustic scene analysis. Proceedings - IEEE International Symposium on Circuits and Systems. 2009. pp. 169-172
@inproceedings{b741e4dfa4a447759eeb11deab647b46,
title = "A sensor network for real-time acoustic scene analysis",
abstract = "Acoustic scene analysis can be used to extract relevant information in applications such as homeland security, surveillance and environmental monitoring. Wireless sensor networks have been of particular interest in monitoring acoustic scenes. Sensors embedded in such a network typically operate under several constraints such as low power and limited bandwidth. In this paper, we consider resource-efficient acoustic sensing tasks that extract and transmit relevant information to a central station where information assessment can be conducted. We propose a series of acoustic scene analysis tasks that are performed in a hierarchical manner. Hierarchical tasks include sound and speech discrimination, estimation of the number of speakers from the acquired sound, gender and emotional state, and ultimately voice monitoring and key word spotting. We apply support vector machine and Gaussian mixture model algorithms on sound features. A real-time implementation is accomplished using Crossbow motes interfaced with a TI DSP board. A series of experiments are presented to characterize the performance of the algorithms under different conditions.",
author = "Homin Kwon and Harish Krishnamoorthi and Visar Berisha and Andreas Spanias",
year = "2009",
doi = "10.1109/ISCAS.2009.5117712",
language = "English (US)",
isbn = "9781424438280",
pages = "169--172",
booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",

}

TY - GEN

T1 - A sensor network for real-time acoustic scene analysis

AU - Kwon, Homin

AU - Krishnamoorthi, Harish

AU - Berisha, Visar

AU - Spanias, Andreas

PY - 2009

Y1 - 2009

N2 - Acoustic scene analysis can be used to extract relevant information in applications such as homeland security, surveillance and environmental monitoring. Wireless sensor networks have been of particular interest in monitoring acoustic scenes. Sensors embedded in such a network typically operate under several constraints such as low power and limited bandwidth. In this paper, we consider resource-efficient acoustic sensing tasks that extract and transmit relevant information to a central station where information assessment can be conducted. We propose a series of acoustic scene analysis tasks that are performed in a hierarchical manner. Hierarchical tasks include sound and speech discrimination, estimation of the number of speakers from the acquired sound, gender and emotional state, and ultimately voice monitoring and key word spotting. We apply support vector machine and Gaussian mixture model algorithms on sound features. A real-time implementation is accomplished using Crossbow motes interfaced with a TI DSP board. A series of experiments are presented to characterize the performance of the algorithms under different conditions.

AB - Acoustic scene analysis can be used to extract relevant information in applications such as homeland security, surveillance and environmental monitoring. Wireless sensor networks have been of particular interest in monitoring acoustic scenes. Sensors embedded in such a network typically operate under several constraints such as low power and limited bandwidth. In this paper, we consider resource-efficient acoustic sensing tasks that extract and transmit relevant information to a central station where information assessment can be conducted. We propose a series of acoustic scene analysis tasks that are performed in a hierarchical manner. Hierarchical tasks include sound and speech discrimination, estimation of the number of speakers from the acquired sound, gender and emotional state, and ultimately voice monitoring and key word spotting. We apply support vector machine and Gaussian mixture model algorithms on sound features. A real-time implementation is accomplished using Crossbow motes interfaced with a TI DSP board. A series of experiments are presented to characterize the performance of the algorithms under different conditions.

UR - http://www.scopus.com/inward/record.url?scp=70350158541&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350158541&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2009.5117712

DO - 10.1109/ISCAS.2009.5117712

M3 - Conference contribution

AN - SCOPUS:70350158541

SN - 9781424438280

SP - 169

EP - 172

BT - Proceedings - IEEE International Symposium on Circuits and Systems

ER -