Detail výsledku

Finite-State Based Recognition Networks For Forward-Backward Speech Decoding

HANNEMANN, M. Finite-State Based Recognition Networks For Forward-Backward Speech Decoding. Brno: Brno University of Technology, 2016. p. 1-105.
Typ
dizertace
Jazyk
angličtina
Autoři
Hannemann Mirko, Ph.D., FIT (FIT), UPGM (FIT)
Abstrakt

This work is about the finite-state based recognition networks for forward-backward speech decoding. The goal of this thesis is to further develop the recipes and algorithms for the construction of optimal recognition networks.

Klíčová slova

Automatic speech recognition, LVCSR decoding, recognition networks, weighted nite state transducers, N-gram language models, weight pushing

URL
Rok
2016
Strany
1–105
Vydavatel
Brno University of Technology
Místo
Brno
BibTeX 
@misc{BUT168579,
  author="Mirko {Hannemann}",
  title="Finite-State Based Recognition Networks For Forward-Backward Speech Decoding",
  year="2016",
  pages="1--105",
  publisher="Brno University of Technology",
  address="Brno",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2016/hannemann_phdthesis_web.pdf"
}
Výzkumné skupiny
Výzkumná skupina dolování dat z řeči BUT Speech@FIT (VZ SPEECH)
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Nahoru