Publication detail

Feature gaussianization in speech recognition

MATĚJKA, P., ČERNOCKÝ, J.

Original Title

Feature gaussianization in speech recognition

Type

conference paper

Language

English

Original Abstract

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.

Keywords

speech recognition, Gaussianization, non-linear transform

Authors

MATĚJKA, P., ČERNOCKÝ, J.

RIV year

2003

Released

16. 5. 2002

Publisher

Slovak University of Technology in Bratislava

Location

Bratislava

ISBN

80-227-1700-2

Book

Proc. 12th International scientific conference Radioelektronika 2002

Pages count

4

URL

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"
}