Detail publikace

VISUAL FEATURES FOR MULTIMODAL SPEECH RECOGNITION

MOTLÍČEK, P., BURGET, L., ČERNOCKÝ, J.

Originální název

VISUAL FEATURES FOR MULTIMODAL SPEECH RECOGNITION

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper demonstrates the use of visual parameters extracted from video for automatic recognition of phoneme strings. Encouraged by previous works utilizing "visually clean" data we investigate their efficiency in non-ideal conditions which are introduced by meeting audio-visual data employed in our experiments.

Klíčová slova

speech recognition, feature extraction, parameterization, visual features, linear transforms, meeting data

Autoři

MOTLÍČEK, P., BURGET, L., ČERNOCKÝ, J.

Rok RIV

2005

Vydáno

16. 5. 2005

Nakladatel

Faculty of Electrical Engineering and Communication BUT

Místo

Brno

ISBN

80-214-2904-6

Kniha

Radioelektronika 2005

Strany od

187

Strany do

190

Strany počet

4

URL

http://www.fit.vutbr.cz/~motlicek/publi/2005/radioel05.pdf, http://wes.feec.vutbr.cz/UREL/

BibTex

@inproceedings{BUT21499,
  author="Petr {Motlíček} and Lukáš {Burget} and Jan {Černocký}",
  title="VISUAL FEATURES FOR MULTIMODAL SPEECH RECOGNITION",
  booktitle="Radioelektronika 2005",
  year="2005",
  pages="187--190",
  publisher="Faculty of Electrical Engineering and Communication BUT",
  address="Brno",
  isbn="80-214-2904-6",
  url="http://www.fit.vutbr.cz/~motlicek/publi/2005/radioel05.pdf, http://wes.feec.vutbr.cz/UREL/"
}