loading
Papers Papers/2020

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Wai Chee Yau 1 ; Dinesh Kant Kumar 1 and Hans Weghorn 2

Affiliations: 1 School of Electrical and Computer Engineering, RMIT University, Australia ; 2 Information Technology, BA-University of Cooperative Education, Germany

Abstract: This paper proposes a machine-learning based technique to investigate the significance of the dynamic information for visual perception of consonants. The visual speech information can be described using static (facial appearance) or dynamic (movement) features. The aim of this research is to determine the saliency of dynamic information represented by the lower facial movement for visual speech perception. The experimental results indicate that the facial movement is distinguishable for nine English consonants with a success rate of 85% using the proposed approach. The results suggest that time-varying information of visual speech contained in lower facial movements is useful for machine recognition of consonants and may be an essential cue for human perception of visual speech.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.236.253.192

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Chee Yau, W.; Kant Kumar, D. and Weghorn, H. (2007). A Machine-learning based Technique to Analyze the Dynamic Information for Visual Perception of Consonants. In Proceedings of the 4th International Workshop on Natural Language Processing and Cognitive Science - NLPCS, (ICEIS 2007) ISBN 978-972-8865-97-9, pages 119-128. DOI: 10.5220/0002424801190128

@conference{nlpcs07,
author={Wai {Chee Yau}. and Dinesh {Kant Kumar}. and Hans Weghorn.},
title={A Machine-learning based Technique to Analyze the Dynamic Information for Visual Perception of Consonants},
booktitle={Proceedings of the 4th International Workshop on Natural Language Processing and Cognitive Science - NLPCS, (ICEIS 2007)},
year={2007},
pages={119-128},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002424801190128},
isbn={978-972-8865-97-9},
}

TY - CONF

JO - Proceedings of the 4th International Workshop on Natural Language Processing and Cognitive Science - NLPCS, (ICEIS 2007)
TI - A Machine-learning based Technique to Analyze the Dynamic Information for Visual Perception of Consonants
SN - 978-972-8865-97-9
AU - Chee Yau, W.
AU - Kant Kumar, D.
AU - Weghorn, H.
PY - 2007
SP - 119
EP - 128
DO - 10.5220/0002424801190128

0123movie.net