Publication Details

VISUAL FEATURES FOR MULTIMODAL SPEECH RECOGNITION

MOTLÍČEK, P.; BURGET, L.; ČERNOCKÝ, J. VISUAL FEATURES FOR MULTIMODAL SPEECH RECOGNITION. Radioelektronika 2005. Brno: Faculty of Electrical Engineering and Communication BUT, 2005. p. 187-190. ISBN: 80-214-2904-6.
Czech title
Video parametry pro multimodální rozpoznávání řeči
Type
conference paper
Language
English
Authors
Motlíček Petr, doc. Ing., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
URL
Keywords

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

Abstract

This paper proposes a bimodal speech recognition scheme using visual parameters extracted from meeting recordings.

Annotation

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.

Published
2005
Pages
187–190
Proceedings
Radioelektronika 2005
ISBN
80-214-2904-6
Publisher
Faculty of Electrical Engineering and Communication BUT
Place
Brno
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="https://www.fit.vut.cz/research/publication/7784/"
}
Back to top