Efficient voice activity detection in reverberant enclosures using far field microphones

Theodore Petsatodis; Christos Boukis

doi:10.1109/ICDSP.2009.5201159

Efficient voice activity detection in reverberant enclosures using far field microphones

Theodore Petsatodis, Christos Boukis

Department of Electronic Systems

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

3 Citations (Scopus)

Abstract

An algorithm suitable for voice activity detection under reverberant conditions is proposed in this paper. Due to the use of far-filed microphones the proposed solution processes speech signals of highly-varying intensity and signal to noise ratio, that are contaminated with several echoes. The core of the system is a pair of Hidden Markov Models, that effectively model the speech presence and speech absence situations. To minimise mis-detections an adaptive threshold is used, while a hang-over scheme caters for the intra-frame correlation of speech signals. Experimental results conducted in a typical office room using a single far field microphone to support the analysis.

Original language	English
Title of host publication	DSP 2009: 16th International Conference on Digital Signal Processing, Proceedings
Number of pages	5
Publisher	IEEE Press
Publication date	2009
Pages	1-5
ISBN (Print)	978-142443298-1, 978-1-4244-3297-4
DOIs	https://doi.org/10.1109/ICDSP.2009.5201159
Publication status	Published - 2009
Event	DSP 2009: 16th International Conference on Digital Signal Processing - Santorini, Greece Duration: 5 Jul 2009 → 7 Jul 2009

Conference

Conference	DSP 2009: 16th International Conference on Digital Signal Processing
Country/Territory	Greece
City	Santorini
Period	05/07/2009 → 07/07/2009

Access to Document

10.1109/ICDSP.2009.5201159

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{0695b75279b34bebb1d3ef6256d97bab,

title = "Efficient voice activity detection in reverberant enclosures using far field microphones",

abstract = "An algorithm suitable for voice activity detection under reverberant conditions is proposed in this paper. Due to the use of far-filed microphones the proposed solution processes speech signals of highly-varying intensity and signal to noise ratio, that are contaminated with several echoes. The core of the system is a pair of Hidden Markov Models, that effectively model the speech presence and speech absence situations. To minimise mis-detections an adaptive threshold is used, while a hang-over scheme caters for the intra-frame correlation of speech signals. Experimental results conducted in a typical office room using a single far field microphone to support the analysis.",

author = "Theodore Petsatodis and Christos Boukis",

note = "Article number 5201159; DSP 2009: 16th International Conference on Digital Signal Processing ; Conference date: 05-07-2009 Through 07-07-2009",

year = "2009",

doi = "10.1109/ICDSP.2009.5201159",

language = "English",

isbn = "978-142443298-1",

pages = "1--5",

booktitle = "DSP 2009: 16th International Conference on Digital Signal Processing, Proceedings",

publisher = "IEEE Press",

}

Petsatodis, T & Boukis, C 2009, Efficient voice activity detection in reverberant enclosures using far field microphones. in DSP 2009: 16th International Conference on Digital Signal Processing, Proceedings. IEEE Press, pp. 1-5, DSP 2009: 16th International Conference on Digital Signal Processing, Santorini, Greece, 05/07/2009. https://doi.org/10.1109/ICDSP.2009.5201159

Efficient voice activity detection in reverberant enclosures using far field microphones. / Petsatodis, Theodore; Boukis, Christos.
DSP 2009: 16th International Conference on Digital Signal Processing, Proceedings. IEEE Press, 2009. p. 1-5.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Efficient voice activity detection in reverberant enclosures using far field microphones

AU - Petsatodis, Theodore

AU - Boukis, Christos

N1 - Article number 5201159

PY - 2009

Y1 - 2009

N2 - An algorithm suitable for voice activity detection under reverberant conditions is proposed in this paper. Due to the use of far-filed microphones the proposed solution processes speech signals of highly-varying intensity and signal to noise ratio, that are contaminated with several echoes. The core of the system is a pair of Hidden Markov Models, that effectively model the speech presence and speech absence situations. To minimise mis-detections an adaptive threshold is used, while a hang-over scheme caters for the intra-frame correlation of speech signals. Experimental results conducted in a typical office room using a single far field microphone to support the analysis.

AB - An algorithm suitable for voice activity detection under reverberant conditions is proposed in this paper. Due to the use of far-filed microphones the proposed solution processes speech signals of highly-varying intensity and signal to noise ratio, that are contaminated with several echoes. The core of the system is a pair of Hidden Markov Models, that effectively model the speech presence and speech absence situations. To minimise mis-detections an adaptive threshold is used, while a hang-over scheme caters for the intra-frame correlation of speech signals. Experimental results conducted in a typical office room using a single far field microphone to support the analysis.

UR - http://www.scopus.com/inward/record.url?scp=70449556346&partnerID=8YFLogxK

U2 - 10.1109/ICDSP.2009.5201159

DO - 10.1109/ICDSP.2009.5201159

M3 - Article in proceeding

AN - SCOPUS:70449556346

SN - 978-142443298-1

SN - 978-1-4244-3297-4

SP - 1

EP - 5

BT - DSP 2009: 16th International Conference on Digital Signal Processing, Proceedings

PB - IEEE Press

T2 - DSP 2009: 16th International Conference on Digital Signal Processing

Y2 - 5 July 2009 through 7 July 2009

ER -

Efficient voice activity detection in reverberant enclosures using far field microphones

Abstract

Conference

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this