Result Details

Context dependent Hidden Markov models in recognition of Czech

KARAFIÁT, M.; ČERNOCKÝ, J. Context dependent Hidden Markov models in recognition of Czech. Proc. 12th International scientific conference Radioelektronika 2002. Bratislava: Slovak University of Technology in Bratislava, 2002. 4 p. ISBN: 80-227-1700-2.
Type
conference paper
Language
English
Authors
Karafiát Martin, Ing., Ph.D., FIT (FIT)
Černocký Jan, prof. Dr. Ing.
Abstract

Context dependent Hidden Markov models in recognition of Czech

Keywords

speech recognition, Hidden Markov models, context, Czech

Annotation

In speech recognition, context dependent (CD) models generally provide better recognition accuracy than context independent (CI) ones. In this paper, we describe the tests of CD models on the recognition of Czech isolated words. The models were trained on SpeechDat-E database. The results with different training setups are presented, and some problems are discussed.

Published
2002
Pages
4
Proceedings
Proc. 12th International scientific conference Radioelektronika 2002
Conference
The 12th International Scientific Conference RADIOELEKTROBIKA 2002
ISBN
80-227-1700-2
Publisher
Slovak University of Technology in Bratislava
Place
Bratislava
BibTeX 
@inproceedings{BUT10262,
  author="Martin {Karafiát} and Jan {Černocký}",
  title="Context dependent Hidden Markov models in recognition of Czech",
  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"
}
Projects
Voice technologies for support of information society, GACR, Standardní projekty, GA102/02/0124, start: 2002-01-01, end: 2004-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Faculty of Information Technology (FIT)
Back to top