Publication detail

Some like it Gaussian ...

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

Original Title

Some like it Gaussian ...

Type

conference paper

Language

English

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.

Key words in English

speech,speech recognition,gaussianization

Authors

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

RIV year

2002

Released

8. 9. 2002

Location

Brno 2002

ISBN

3-540-44129-8

Book

Proceedings of the conference TSD'2002

Edition number

1

Pages from

321

Pages to

324

Pages count

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",
  number="1",
  pages="4",
  address="Brno 2002",
  isbn="3-540-44129-8"
}