Detail publikace

Some like it Gaussian

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

Český název

Some like it Gaussian

Anglický název

Some like it Gaussian ...

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

en

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.

Český abstrakt

Some like it Gaussian

Anglický 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 anglicky

speech,speech recognition,gaussianization

Rok RIV

2002

Vydáno

08.09.2002

Místo

Brno 2002

ISBN

3-540-44129-8

Kniha

Proceedings of the conference TSD'2002

Číslo edice

1

Počet stran

4

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",
  month="September",
  address="Brno 2002",
  isbn="3-540-44129-8"
}