Detail publikace

VISUAL FEATURES FOR MULTIMODAL SPEECH RECOGNITION

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

Originální název

VISUAL FEATURES FOR MULTIMODAL SPEECH RECOGNITION

Anglický název

VISUAL FEATURES FOR MULTIMODAL SPEECH RECOGNITION

Jazyk

en

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.

Anglický 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.

Dokumenty

BibTex


@inproceedings{BUT21499,
  author="Petr {Motlíček} and Lukáš {Burget} and Jan {Černocký}",
  title="VISUAL FEATURES FOR MULTIMODAL SPEECH RECOGNITION",
  annote="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.",
  address="Faculty of Electrical Engineering and Communication BUT",
  booktitle="Radioelektronika 2005",
  chapter="21499",
  institution="Faculty of Electrical Engineering and Communication BUT",
  year="2005",
  month="may",
  pages="187--190",
  publisher="Faculty of Electrical Engineering and Communication BUT",
  type="conference paper"
}