Publication detail

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

KARAFIÁT, M.

Original Title

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

Type

dissertation

Language

English

Original Abstract

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.

Keywords

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

Authors

KARAFIÁT, M.

Released

5. 2. 2009

Location

Brno

Pages count

73

URL

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

BibTex

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