Detail publikace

Context dependent Hidden Markov models in recognition of Czech

Originální název

Context dependent Hidden Markov models in recognition of Czech

Anglický název

Context dependent Hidden Markov models in recognition of Czech

Jazyk

en

Originální abstrakt

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.

Anglický abstrakt

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.

BibTex


@inproceedings{BUT10262,
  author="Martin {Karafiát} and Jan {Černocký}",
  title="Context dependent Hidden Markov models in recognition of Czech",
  annote="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.",
  address="Slovak University of Technology in Bratislava",
  booktitle="Proc. 12th International scientific conference Radioelektronika 2002",
  chapter="10262",
  institution="Slovak University of Technology in Bratislava",
  year="2002",
  month="may",
  pages="0",
  publisher="Slovak University of Technology in Bratislava",
  type="conference paper"
}