Robust Speaker Verification in Air Traffic Control using Improved Voice Activity Detection

Michael Stark; Van Tuan Pham; Franz Pernkopf; Gernot Kubin

Robust Speaker Verification in Air Traffic Control using Improved Voice Activity Detection

Michael Stark
, Van Tuan Pham
, Franz Pernkopf
, Gernot Kubin

Institute of Signal Processing and Speech Communication (4420)

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Abstract

In this paper, a robust speaker verification system using improved voice activity detection has been designed for increasing safety of air traffic control. In addition to the usage of the aircraft identification tag to assign speaker turns on the shared communication channel to aircrafts,
speaker verification is investigated as an add-on attribute to improve security level effectively for the air traffic control. The front-end processing unit is optimized to deal with small bandwidth restrictions and very short speaker turns. Two adaptive voice activity detection methods based on energy and wavelet parameters are developed and used as pre-processing in front-end unit. The verification task is accomplished by training background models and speaker dependent models. To enhance the robustness of the verification system, a cross verification unit is further applied.
The designed system is tested with SPEECHDAT-AT and WSJ0 database to demonstrate its superior performance.

Original language	English
Title of host publication	Proceedings of the Fourth IASTED International Conference Signal Processing, Pattern Recognition, and Applications
Place of Publication	Anaheim, Ca.
Publisher	Acta Press
Pages	298-303
ISBN (Print)	978-0-88986-646-1
Publication status	Published - 2007
Event	4th IASTED International Conference Signal Processing, Pattern Recognition, and Applications: SPPR 2007 - Innsbruck, Austria Duration: 14 Feb 2007 → 16 Feb 2007

Conference

Conference	4th IASTED International Conference Signal Processing, Pattern Recognition, and Applications
Abbreviated title	SPPR'07
Country/Territory	Austria
City	Innsbruck
Period	14/02/07 → 16/02/07

Treatment code (Nähere Zuordnung)

Basic - Fundamental (Grundlagenforschung)
Application
Popular Scientific

Access to Document

554-139Final published version, 936 KB

Cite this

Robust Speaker Verification in Air Traffic Control using Improved Voice Activity Detection. / Stark, Michael; Pham, Van Tuan; Pernkopf, Franz et al.
Proceedings of the Fourth IASTED International Conference Signal Processing, Pattern Recognition, and Applications. Anaheim, Ca.: Acta Press, 2007. p. 298-303.

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Stark, M, Pham, VT, Pernkopf, F & Kubin, G 2007, Robust Speaker Verification in Air Traffic Control using Improved Voice Activity Detection. in Proceedings of the Fourth IASTED International Conference Signal Processing, Pattern Recognition, and Applications. Acta Press, Anaheim, Ca., pp. 298-303, 4th IASTED International Conference Signal Processing, Pattern Recognition, and Applications, Innsbruck, Austria, 14/02/07.

@inproceedings{915e1bdf386442038892940112eff5aa,

title = "Robust Speaker Verification in Air Traffic Control using Improved Voice Activity Detection",

abstract = "In this paper, a robust speaker verification system using improved voice activity detection has been designed for increasing safety of air traffic control. In addition to the usage of the aircraft identification tag to assign speaker turns on the shared communication channel to aircrafts, speaker verification is investigated as an add-on attribute to improve security level effectively for the air traffic control. The front-end processing unit is optimized to deal with small bandwidth restrictions and very short speaker turns. Two adaptive voice activity detection methods based on energy and wavelet parameters are developed and used as pre-processing in front-end unit. The verification task is accomplished by training background models and speaker dependent models. To enhance the robustness of the verification system, a cross verification unit is further applied. The designed system is tested with SPEECHDAT-AT and WSJ0 database to demonstrate its superior performance.",

author = "Michael Stark and Pham, \{Van Tuan\} and Franz Pernkopf and Gernot Kubin",

year = "2007",

language = "English",

isbn = "978-0-88986-646-1",

pages = "298--303",

booktitle = "Proceedings of the Fourth IASTED International Conference Signal Processing, Pattern Recognition, and Applications",

publisher = "Acta Press",

note = "4th IASTED International Conference Signal Processing, Pattern Recognition, and Applications : SPPR 2007, SPPR'07 ; Conference date: 14-02-2007 Through 16-02-2007",

}

TY - GEN

T1 - Robust Speaker Verification in Air Traffic Control using Improved Voice Activity Detection

AU - Stark, Michael

AU - Pham, Van Tuan

AU - Pernkopf, Franz

AU - Kubin, Gernot

PY - 2007

Y1 - 2007

N2 - In this paper, a robust speaker verification system using improved voice activity detection has been designed for increasing safety of air traffic control. In addition to the usage of the aircraft identification tag to assign speaker turns on the shared communication channel to aircrafts, speaker verification is investigated as an add-on attribute to improve security level effectively for the air traffic control. The front-end processing unit is optimized to deal with small bandwidth restrictions and very short speaker turns. Two adaptive voice activity detection methods based on energy and wavelet parameters are developed and used as pre-processing in front-end unit. The verification task is accomplished by training background models and speaker dependent models. To enhance the robustness of the verification system, a cross verification unit is further applied. The designed system is tested with SPEECHDAT-AT and WSJ0 database to demonstrate its superior performance.

AB - In this paper, a robust speaker verification system using improved voice activity detection has been designed for increasing safety of air traffic control. In addition to the usage of the aircraft identification tag to assign speaker turns on the shared communication channel to aircrafts, speaker verification is investigated as an add-on attribute to improve security level effectively for the air traffic control. The front-end processing unit is optimized to deal with small bandwidth restrictions and very short speaker turns. Two adaptive voice activity detection methods based on energy and wavelet parameters are developed and used as pre-processing in front-end unit. The verification task is accomplished by training background models and speaker dependent models. To enhance the robustness of the verification system, a cross verification unit is further applied. The designed system is tested with SPEECHDAT-AT and WSJ0 database to demonstrate its superior performance.

M3 - Conference paper

SN - 978-0-88986-646-1

SP - 298

EP - 303

BT - Proceedings of the Fourth IASTED International Conference Signal Processing, Pattern Recognition, and Applications

PB - Acta Press

CY - Anaheim, Ca.

T2 - 4th IASTED International Conference Signal Processing, Pattern Recognition, and Applications

Y2 - 14 February 2007 through 16 February 2007

ER -

Robust Speaker Verification in Air Traffic Control using Improved Voice Activity Detection

Abstract

Conference

Treatment code (Nähere Zuordnung)

Access to Document

Fingerprint

Cite this