Abstract

Wireless sensor networks (WSN) have recently gained popularity in distributed monitoring and surveillance applications. The objective of these devices is to extract pertinent information under several constrains such as low computational capabilities, limited arithmetic precision, and the need to conserve power. One of the most revealing environmental cues is audio. In this paper, we propose a voice activity detector and a simple gender classifier for use in a distributed acoustic sensing system. This algorithm makes use of low-complexity audio features and a pre-trained regression tree to classify incoming speech by gender. The algorithm is implemented real-time on the Crossbow sensor motes and a series of results are given that characterize the algorithm performance and complexity. Challenges in this real-time implementation include designing the algorithm and software architecture such that the signal processing is appropriately distributed between the sensor mote and the base station. At the base station, a data fusion algorithm considers a linear combination of individual mote decisions to form a final decision.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Symposium on Circuits and Systems
Pages847-850
Number of pages4
StatePublished - 2006
EventISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems - Kos, Greece
Duration: May 21 2006May 24 2006

Other

OtherISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems
CountryGreece
CityKos
Period5/21/065/24/06

Fingerprint

Acoustics
Monitoring
Sensors
Base stations
Data fusion
Software architecture
Wireless sensor networks
Signal processing
Classifiers
Detectors

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Cite this

Berisha, V., Kwon, H., & Spanias, A. (2006). Real-time acoustic monitoring using wireless sensor motes. In Proceedings - IEEE International Symposium on Circuits and Systems (pp. 847-850). [1692718]

Real-time acoustic monitoring using wireless sensor motes. / Berisha, Visar; Kwon, Homin; Spanias, Andreas.

Proceedings - IEEE International Symposium on Circuits and Systems. 2006. p. 847-850 1692718.

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

Berisha, V, Kwon, H & Spanias, A 2006, Real-time acoustic monitoring using wireless sensor motes. in Proceedings - IEEE International Symposium on Circuits and Systems., 1692718, pp. 847-850, ISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems, Kos, Greece, 5/21/06.
Berisha V, Kwon H, Spanias A. Real-time acoustic monitoring using wireless sensor motes. In Proceedings - IEEE International Symposium on Circuits and Systems. 2006. p. 847-850. 1692718
Berisha, Visar ; Kwon, Homin ; Spanias, Andreas. / Real-time acoustic monitoring using wireless sensor motes. Proceedings - IEEE International Symposium on Circuits and Systems. 2006. pp. 847-850
@inproceedings{dffb8df322424b699e0909324f14bb68,
title = "Real-time acoustic monitoring using wireless sensor motes",
abstract = "Wireless sensor networks (WSN) have recently gained popularity in distributed monitoring and surveillance applications. The objective of these devices is to extract pertinent information under several constrains such as low computational capabilities, limited arithmetic precision, and the need to conserve power. One of the most revealing environmental cues is audio. In this paper, we propose a voice activity detector and a simple gender classifier for use in a distributed acoustic sensing system. This algorithm makes use of low-complexity audio features and a pre-trained regression tree to classify incoming speech by gender. The algorithm is implemented real-time on the Crossbow sensor motes and a series of results are given that characterize the algorithm performance and complexity. Challenges in this real-time implementation include designing the algorithm and software architecture such that the signal processing is appropriately distributed between the sensor mote and the base station. At the base station, a data fusion algorithm considers a linear combination of individual mote decisions to form a final decision.",
author = "Visar Berisha and Homin Kwon and Andreas Spanias",
year = "2006",
language = "English (US)",
isbn = "0780393902",
pages = "847--850",
booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",

}

TY - GEN

T1 - Real-time acoustic monitoring using wireless sensor motes

AU - Berisha, Visar

AU - Kwon, Homin

AU - Spanias, Andreas

PY - 2006

Y1 - 2006

N2 - Wireless sensor networks (WSN) have recently gained popularity in distributed monitoring and surveillance applications. The objective of these devices is to extract pertinent information under several constrains such as low computational capabilities, limited arithmetic precision, and the need to conserve power. One of the most revealing environmental cues is audio. In this paper, we propose a voice activity detector and a simple gender classifier for use in a distributed acoustic sensing system. This algorithm makes use of low-complexity audio features and a pre-trained regression tree to classify incoming speech by gender. The algorithm is implemented real-time on the Crossbow sensor motes and a series of results are given that characterize the algorithm performance and complexity. Challenges in this real-time implementation include designing the algorithm and software architecture such that the signal processing is appropriately distributed between the sensor mote and the base station. At the base station, a data fusion algorithm considers a linear combination of individual mote decisions to form a final decision.

AB - Wireless sensor networks (WSN) have recently gained popularity in distributed monitoring and surveillance applications. The objective of these devices is to extract pertinent information under several constrains such as low computational capabilities, limited arithmetic precision, and the need to conserve power. One of the most revealing environmental cues is audio. In this paper, we propose a voice activity detector and a simple gender classifier for use in a distributed acoustic sensing system. This algorithm makes use of low-complexity audio features and a pre-trained regression tree to classify incoming speech by gender. The algorithm is implemented real-time on the Crossbow sensor motes and a series of results are given that characterize the algorithm performance and complexity. Challenges in this real-time implementation include designing the algorithm and software architecture such that the signal processing is appropriately distributed between the sensor mote and the base station. At the base station, a data fusion algorithm considers a linear combination of individual mote decisions to form a final decision.

UR - http://www.scopus.com/inward/record.url?scp=34547354376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547354376&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:34547354376

SN - 0780393902

SN - 9780780393905

SP - 847

EP - 850

BT - Proceedings - IEEE International Symposium on Circuits and Systems

ER -