Publication Details

Some like it Gaussian...

MATĚJKA Pavel, SCHWARZ Petr, KARAFIÁT Martin and ČERNOCKÝ Jan. Some like it Gaussian... In: Proc. 5th International Conference Text, Speech and Dialogue, TSD2002. Lecture notes in artificial intelligence 2448. Berlin: Springer Verlag, 2002, pp. 321-324. ISBN 3-540-44129-8.
Czech title
Někdo to má rád Gausianizované ...
Type
conference paper
Language
english
Authors
Matějka Pavel, Ing. (UREL FEEC BUT)
Schwarz Petr, Ing., Ph.D. (DCGM FIT BUT)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
URL
Keywords

speech recognition, feature extraction, Gaussianization, non-linear transform

Abstract

Gaussianization of speech features to improve recognition accuracy

Annotation

In Hidden Markov models, speech features 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 have tested two methods of the transform estimation (global and speaker based). The results are reported on recognition of isolated Czech words (SpeechDat-E) with CI and CD models and on medium vocabulary continuous speech recognition task (SPINE). Gaussianized data provided in all three cases results superior to standard MFC coefficients proving, that the gaussianization is a cheap way to increase the recognition accuracy

Published
2002
Pages
321-324
Proceedings
Proc. 5th International Conference Text, Speech and Dialogue, TSD2002
Series
Lecture notes in artificial intelligence 2448
Conference
5th International conference Text, Speech and Dialogue, TSD 2002, Brno, CZ
ISBN
3-540-44129-8
Publisher
Springer Verlag
Place
Berlin, DE
BibTeX
@INPROCEEDINGS{FITPUB7025,
   author = "Pavel Mat\v{e}jka and Petr Schwarz and Martin Karafi\'{a}t and Jan \v{C}ernock\'{y}",
   title = "Some like it Gaussian...",
   pages = "321--324",
   booktitle = "Proc. 5th International Conference Text, Speech and Dialogue, TSD2002",
   series = "Lecture notes in artificial intelligence 2448",
   year = 2002,
   location = "Berlin, DE",
   publisher = "Springer Verlag",
   ISBN = "3-540-44129-8",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/7025"
}
Back to top