Abstract

Wireless sensor networks have been applied successfully in real-time distributed and collaborative sensing. In these situations, each sensor is responsible for extracting pertinent information from the surrounding environment and transmitting it to other sensors and/or to the main processing station. This is done while operating under several constraints, such as low computational capabilities, limited arithmetic precision, and the need to conserve power. In this paper, we present a low-complexity voice activity detector and a gender classifier for implementation on the Crossbow sensor motes. In addition, a decision fusion algorithm that resides at the base station is also implemented. A series of experiments that characterize the performance of the algorithms under varying conditions and in different environments are presented and several of the challenges we faced in developing this real-time implementation are discussed.

Original languageEnglish (US)
Title of host publication2006 IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006
Pages659-662
Number of pages4
StatePublished - 2006
Event4th IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006 - Waltham, MA, United States
Duration: Jul 12 2006Jul 14 2006

Other

Other4th IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006
CountryUnited States
CityWaltham, MA
Period7/12/067/14/06

Fingerprint

Detectors
Sensors
Base stations
Wireless sensor networks
Classifiers
Fusion reactions
Processing
Experiments

ASJC Scopus subject areas

  • Signal Processing
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Berisha, V., Kwon, H., & Spanias, A. (2006). Real-time implementation of a distributed voice activity detector. In 2006 IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006 (pp. 659-662)

Real-time implementation of a distributed voice activity detector. / Berisha, Visar; Kwon, Homin; Spanias, Andreas.

2006 IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006. 2006. p. 659-662.

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

Berisha, V, Kwon, H & Spanias, A 2006, Real-time implementation of a distributed voice activity detector. in 2006 IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006. pp. 659-662, 4th IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006, Waltham, MA, United States, 7/12/06.
Berisha V, Kwon H, Spanias A. Real-time implementation of a distributed voice activity detector. In 2006 IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006. 2006. p. 659-662
Berisha, Visar ; Kwon, Homin ; Spanias, Andreas. / Real-time implementation of a distributed voice activity detector. 2006 IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006. 2006. pp. 659-662
@inproceedings{fd91425932e045a1894a4c60109fc8d0,
title = "Real-time implementation of a distributed voice activity detector",
abstract = "Wireless sensor networks have been applied successfully in real-time distributed and collaborative sensing. In these situations, each sensor is responsible for extracting pertinent information from the surrounding environment and transmitting it to other sensors and/or to the main processing station. This is done while operating under several constraints, such as low computational capabilities, limited arithmetic precision, and the need to conserve power. In this paper, we present a low-complexity voice activity detector and a gender classifier for implementation on the Crossbow sensor motes. In addition, a decision fusion algorithm that resides at the base station is also implemented. A series of experiments that characterize the performance of the algorithms under varying conditions and in different environments are presented and several of the challenges we faced in developing this real-time implementation are discussed.",
author = "Visar Berisha and Homin Kwon and Andreas Spanias",
year = "2006",
language = "English (US)",
isbn = "1424403081",
pages = "659--662",
booktitle = "2006 IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006",

}

TY - GEN

T1 - Real-time implementation of a distributed voice activity detector

AU - Berisha, Visar

AU - Kwon, Homin

AU - Spanias, Andreas

PY - 2006

Y1 - 2006

N2 - Wireless sensor networks have been applied successfully in real-time distributed and collaborative sensing. In these situations, each sensor is responsible for extracting pertinent information from the surrounding environment and transmitting it to other sensors and/or to the main processing station. This is done while operating under several constraints, such as low computational capabilities, limited arithmetic precision, and the need to conserve power. In this paper, we present a low-complexity voice activity detector and a gender classifier for implementation on the Crossbow sensor motes. In addition, a decision fusion algorithm that resides at the base station is also implemented. A series of experiments that characterize the performance of the algorithms under varying conditions and in different environments are presented and several of the challenges we faced in developing this real-time implementation are discussed.

AB - Wireless sensor networks have been applied successfully in real-time distributed and collaborative sensing. In these situations, each sensor is responsible for extracting pertinent information from the surrounding environment and transmitting it to other sensors and/or to the main processing station. This is done while operating under several constraints, such as low computational capabilities, limited arithmetic precision, and the need to conserve power. In this paper, we present a low-complexity voice activity detector and a gender classifier for implementation on the Crossbow sensor motes. In addition, a decision fusion algorithm that resides at the base station is also implemented. A series of experiments that characterize the performance of the algorithms under varying conditions and in different environments are presented and several of the challenges we faced in developing this real-time implementation are discussed.

UR - http://www.scopus.com/inward/record.url?scp=34250684510&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250684510&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:34250684510

SN - 1424403081

SN - 9781424403080

SP - 659

EP - 662

BT - 2006 IEEE Sensor Array and Multichannel Signal Processing Workshop Proceedings, SAM 2006

ER -