Publication detail

Some like it Gaussian...

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

Original Title

Some like it Gaussian...

English Title

Some like it Gaussian...

Type

conference paper

Language

en

Original Abstract

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

English abstract

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

Keywords

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

RIV year

2002

Released

30.09.2002

Publisher

Springer Verlag

Location

Berlin

ISBN

3-540-44129-8

Book

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

Edition

Lecture notes in artificial intelligence 2448

Pages from

321

Pages to

324

Pages count

4

URL

Documents

BibTex


@inproceedings{BUT10260,
  author="Pavel {Matějka} and Petr {Schwarz} and Martin {Karafiát} and Jan {Černocký}",
  title="Some like it Gaussian...",
  annote="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",
  address="Springer Verlag",
  booktitle="Proc. 5th International Conference Text, Speech and Dialogue, TSD2002",
  chapter="10260",
  edition="Lecture notes in artificial intelligence 2448",
  institution="Springer Verlag",
  year="2002",
  month="september",
  pages="321--324",
  publisher="Springer Verlag",
  type="conference paper"
}