Detail publikačního výsledku

Study of linear transformations applied to training of cross-domain adapted large vocabulary continuous speech recognition systems

KARAFIÁT, M.

Originální název

Study of linear transformations applied to training of cross-domain adapted large vocabulary continuous speech recognition systems

Anglický název

Study of linear transformations applied to training of cross-domain adapted large vocabulary continuous speech recognition systems

Druh

Dizertace

Originální abstrakt

This thesis investigates into two important issues of acoustic modeling for automatic speech recognition (ASR).  The second part deals with using heterogeneous data resources in ASR training.

Anglický abstrakt

This thesis investigates into two important issues of acoustic modeling for automatic speech recognition (ASR).  The second part deals with using heterogeneous data resources in ASR training.

Klíčová slova

LVCSR system, meeting recognition, linear transform, Adaptation, cross domain adaptation, HLDA, CMLLR, MLLR, narrow band - wide band

Klíčová slova v angličtině

LVCSR system, meeting recognition, linear transform, Adaptation, cross domain adaptation, HLDA, CMLLR, MLLR, narrow band - wide band

Autoři

KARAFIÁT, M.

Vydáno

05.02.2009

Místo

Brno

Strany počet

73

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2009/karafiat_thesis.pdf

BibTex

@misc{BUT192664,
  author="Martin {Karafiát}",
  title="Study of linear transformations applied to training of cross-domain adapted large vocabulary continuous speech recognition systems",
  year="2009",
  pages="73",
  address="Brno",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2009/karafiat_thesis.pdf"
}