Frame Rate and Viseme Analysis for Multimedia Applications toAssist Speechreading

Authors:
Jay J. Williams;Janet C. Rutledge;Aggelos K. Katsaggelos;Dean C. Garstecki
Affiliations:
Department of Electrical and Computer Engineering, Northwestern University, Evanston IL 60208;Department of Electrical and Computer Engineering, Northwestern University, Evanston IL 60208;Department of Electrical and Computer Engineering, Northwestern University, Evanston IL 60208;Department of Communication Sciences and Disorders, Northwestern University, Evanston IL 60208
Venue:
Journal of VLSI Signal Processing Systems - special issue on multimedia signal processing
Year:
1998

Citing 3
Cited 3

Fundamentals of speech recognition

Fundamentals of speech recognition
The voice of the computer is heard in the land (and it listens too!)

IEEE Spectrum
Frame Rate and Viseme Analysis for Multimedia Applications toAssist Speechreading

Journal of VLSI Signal Processing Systems - special issue on multimedia signal processing

Frame Rate and Viseme Analysis for Multimedia Applications toAssist Speechreading

Journal of VLSI Signal Processing Systems - special issue on multimedia signal processing
Persian Viseme Classification for Developing Visual Speech Training Application

PCM '09 Proceedings of the 10th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Clustering Persian viseme using phoneme subspace for developing visual speech application

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Current video conference and phone systems do not provide the necessarytemporal resolution and motion for speechreading. In this paper theperceptual boundaries which effect speechreading performance areinvestigated. Analysis of the relationships between viseme groupings,accuracy of viseme recognition and presentation frame rate is presentedbased on the results of subject testing. Results reveal a minimum framerate of 10 frames per second (fps) for distinguishing viseme groupings.Confusion analysis results demonstrate the importance of the tongue andteeth oral features for speechreading. These results are critical to thedesign of speech-assisted video systems to enhance speechreading forindividuals with impaired hearing.