Detail publikace

Convolutive Bottleneck Network Features for LVCSR

VESELÝ, K. KARAFIÁT, M. GRÉZL, F.

Originální název

Convolutive Bottleneck Network Features for LVCSR

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

Workshop Article about novel features for tandem LVCSR system, which are based on Convolutive Bottleneck Network. It extends the previous work on Universal Context network by using linear bottleneck and expansion to Convolutive Bottleneck Network,

so all the parameters are trained together.

Klíčová slova

Bottleneck features, Tandem LVCSR system,linear bottleneck, Convolutional Bottleneck Network

Autoři

VESELÝ, K.; KARAFIÁT, M.; GRÉZL, F.

Rok RIV

2011

Vydáno

11. 12. 2011

Nakladatel

IEEE Signal Processing Society

Místo

Big Island, Hawaii

ISBN

978-1-4673-0366-8

Kniha

Proceedings of ASRU 2011

Strany od

42

Strany do

47

Strany počet

6

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2011/vesely_asru2011_00042.pdf

BibTex

@inproceedings{BUT76443,
  author="Karel {Veselý} and Martin {Karafiát} and František {Grézl}",
  title="Convolutive Bottleneck Network Features for LVCSR",
  booktitle="Proceedings of ASRU 2011",
  year="2011",
  pages="42--47",
  publisher="IEEE Signal Processing Society",
  address="Big Island, Hawaii",
  isbn="978-1-4673-0366-8",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2011/vesely_asru2011_00042.pdf"
}