Result Details
Feature gaussianization in speech recognition
MATĚJKA, P.; ČERNOCKÝ, J. Feature gaussianization in speech recognition. Proc. 12th International scientific conference Radioelektronika 2002. Bratislava: Slovak University of Technology in Bratislava, 2002. 4 p. ISBN: 80-227-1700-2.
Type
conference paper
Language
English
Authors
Matějka Pavel, Ing., Ph.D., UREL (FEEC)
Černocký Jan, prof. Dr. Ing.
Černocký Jan, prof. Dr. Ing.
Abstract
Feature gaussianization in speech recognition
Keywords
speech recognition, Gaussianization, non-linear transform
URL
Annotation
In Hidden Markov models, speech data are modeled by Gaussian distributions. In this paper, we propose to Gaussianize the features to better fit to this modeling. A distribution of the data is estimated and a transform function is derived. We test three methods of the transform estimation (global, speaker based, frame based) and report results on the SPINE 2000 task with SPhinx recognizer. We conclude that the proposed method is a cheap way to increase the recognition accuracy.
Published
2002
Pages
4
Proceedings
Proc. 12th International scientific conference Radioelektronika 2002
Conference
The 12th International Scientific Conference RADIOELEKTROBIKA 2002
ISBN
80-227-1700-2
Publisher
Slovak University of Technology in Bratislava
Place
Bratislava
BibTeX
@inproceedings{BUT10283,
author="Pavel {Matějka} and Jan {Černocký}",
title="Feature gaussianization in speech recognition",
booktitle="Proc. 12th International scientific conference Radioelektronika 2002",
year="2002",
pages="4",
publisher="Slovak University of Technology in Bratislava",
address="Bratislava",
isbn="80-227-1700-2",
url="http://www.fit.vutbr.cz/~matejkap/publi/2002/RA2002.pdf"
}
Projects
Voice technologies for support of information society, GACR, Standardní projekty, GA102/02/0124, start: 2002-01-01, end: 2004-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments