Skip to content

Detail of publication


Trmal, J. and Vaněk, J. and Müller, L. and Zelinka, J. : Independent components for acoustic modeling . Interspeech, vol. 1, p. 2486-2489, ISCA, Bonn, 2006.

Download PDF



In the paper, we present a comparative study of several methods used nowadays in the field of feature and information extraction. We compared several Independent Component Analysis (ICA) algorithms together with the commonly used Principal Component Analysis (PCA) algorithm in two real-world tasks. The first task was a Voice Activity Detection (VAD), the second is Speaker Verification and Recognition (SVR). The VAD system as well as the SVR system benefited from the ICA decompositions. Moreover, a brief comparison of the information extraction ability is described.

Detail of publication

Title: Independent components for acoustic modeling
Author: Trmal, J. ; Vaněk, J. ; Müller, L. ; Zelinka, J.
Language: English
Date of publication: 17 Sep 2006
Year: 2006
Type of publication: Papers in journals
Title of journal or book: Interspeech
Číslo vydání: 1
Page: 2486 - 2489
ISBN: 1990-9772
ISSN: 1990-9772
Publisher: ISCA
Address: Bonn
Date: 17 Sep 2006 - 21 Sep 2006
/ 2012-02-17 11:13:50 /


independent components, principal components, ICA, linear transforms, speaker verification, recognition, voice activity detection


 author = {Trmal, J. and Van\v{e}k, J. and M\"{u}ller, L. and Zelinka, J.},
 title = {Independent components for acoustic modeling},
 year = {2006},
 publisher = {ISCA},
 journal = {Interspeech},
 address = {Bonn},
 volume = {1},
 pages = {2486-2489},
 ISBN = {1990-9772},
 ISSN = {1990-9772},
 url = {},