Skip to content

Publications

Detail of publication

Citation

Psutka, Josef V. and Müller, L. : Comparison of various feature decorrelation techniques in automatic speech recognition . CITSA 2006, p. 165-168, IIIS, Orlando, 2006.

Abstract

The design of an optimum front-end module for an automatic speech recognition system is still a great effort of many research teams all over the world. Prepared paper wants to contribute partly to these discussions. It is especially aimed at feature decorrelation techniques based on Maximum Linear Likelihood Transform (MLLT) applied at a different level of matrix clustering. Also the comparison of the MLLT with other decorrelation techniques will be discussed.

Detail of publication

Title: Comparison of various feature decorrelation techniques in automatic speech recognition
Author: Psutka, Josef V. ; Müller, L.
Language: English
Date of publication: 20 Jul 2006
Year: 2006
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: CITSA 2006
Page: 165 - 168
ISBN: 980-6560-82-5
Publisher: IIIS
Address: Orlando
Date: 20 Jul 2006 - 23 Jul 2006
/ 2011-06-08 16:49:24 /

Keywords

speech parameterization, decorrelation techniques, MLLT

BibTeX

@INPROCEEDINGS{PsutkaJosefV_2006_Comparisonofvarious,
 author = {Psutka, Josef V. and M\"{u}ller, L.},
 title = {Comparison of various feature decorrelation techniques in automatic speech recognition},
 year = {2006},
 publisher = {IIIS},
 journal = {CITSA 2006},
 address = {Orlando},
 pages = {165-168},
 ISBN = {980-6560-82-5},
 url = {http://www.kky.zcu.cz/en/publications/PsutkaJosefV_2006_Comparisonofvarious},
}