Detail publikace

Some like it Gaussian...

MATĚJKA, P., SCHWARZ, P., KARAFIÁT, M., ČERNOCKÝ, J.

Originální název

Some like it Gaussian...

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální 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

Klíčová slova

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

Autoři

MATĚJKA, P., SCHWARZ, P., KARAFIÁT, M., ČERNOCKÝ, J.

Rok RIV

2002

Vydáno

30. 9. 2002

Nakladatel

Springer Verlag

Místo

Berlin

ISBN

3-540-44129-8

Kniha

Proc. 5th International Conference Text, Speech and Dialogue, TSD2002

Edice

Lecture notes in artificial intelligence 2448

Strany od

321

Strany do

324

Strany počet

4

URL

http://www.fit.vutbr.cz/~matejkap/publi/2002/tsd2002.pdf

BibTex

@inproceedings{BUT10260,
  author="Pavel {Matějka} and Petr {Schwarz} and Martin {Karafiát} and Jan {Černocký}",
  title="Some like it Gaussian...",
  booktitle="Proc. 5th International Conference Text, Speech and Dialogue, TSD2002",
  year="2002",
  series="Lecture notes in artificial intelligence 2448",
  pages="321--324",
  publisher="Springer Verlag",
  address="Berlin",
  isbn="3-540-44129-8",
  url="http://www.fit.vutbr.cz/~matejkap/publi/2002/tsd2002.pdf"
}