Detail publikace

Feature gaussianization in speech recognition

MATĚJKA, P., ČERNOCKÝ, J.

Originální název

Feature gaussianization in speech recognition

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

In Hidden Markov models, speech data 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 test three methods of the transform estimation (global, speaker based, frame based) and report results on the SPINE 2000 task with SPhinx recognizer. We conclude that the proposed method is a cheap way to increase the recognition accuracy.

Klíčová slova

speech recognition, Gaussianization, non-linear transform

Autoři

MATĚJKA, P., ČERNOCKÝ, J.

Rok RIV

2003

Vydáno

16. 5. 2002

Nakladatel

Slovak University of Technology in Bratislava

Místo

Bratislava

ISBN

80-227-1700-2

Kniha

Proc. 12th International scientific conference Radioelektronika 2002

Strany počet

4

URL

http://www.fit.vutbr.cz/~matejkap/publi/2002/RA2002.pdf

BibTex

@inproceedings{BUT10283,
  author="Pavel {Matějka} and Jan {Černocký}",
  title="Feature gaussianization in speech recognition",
  booktitle="Proc. 12th International scientific conference Radioelektronika 2002",
  year="2002",
  pages="4",
  publisher="Slovak University of Technology in Bratislava",
  address="Bratislava",
  isbn="80-227-1700-2",
  url="http://www.fit.vutbr.cz/~matejkap/publi/2002/RA2002.pdf"
}