Detail výsledku

Some like it Gaussian ...

MATĚJKA, P., SCHWARZ, P., KARAFIÁT, M., ČERNOCKÝ, J. Some like it Gaussian ... In Proceedings of the conference TSD'2002. Brno 2002: 2002. 4 p. ISBN: 3-540-44129-8.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Matějka Pavel, Ing., Ph.D., UREL (FEKT)
Schwarz Petr, Ing., Ph.D., FIT (FIT)
Karafiát Martin, Ing., Ph.D., FIT (FIT)
Černocký Jan, prof. Dr. Ing.
Abstrakt

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.

Rok
2002
Strany
4
Sborník
Proceedings of the conference TSD'2002
Vydání
1
Konference
International Conference on Text Speech and Dialogue, TSD 2002
ISBN
3-540-44129-8
Místo
Brno 2002
BibTeX 
@inproceedings{BUT4282,
  author="Pavel {Matějka} and Petr {Schwarz} and Martin {Karafiát} and Jan {Černocký}",
  title="Some like it Gaussian ...",
  booktitle="Proceedings of the conference TSD'2002",
  year="2002",
  number="1",
  pages="4",
  address="Brno 2002",
  isbn="3-540-44129-8"
}
Pracoviště
Ústav radioelektroniky (UREL)
Nahoru