Abstract
Deaf people can restore by speechreading about 50% of the information by observing the motions of their speaker’s lips. This high error level is due to the existence of double lip form for some sounds. These forms are tied to the phonetic features and by detecting the features many of these double lip forms can be avoided.
The aim of our application is to give additional information, based on phonetic feature recognition, to deaf people to help them with speechreading. In fact, the aim is to display the phonetic features detected and the corresponding lip form on the screen of a multimedia communication system.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Sokol, R., Mercier, G. (1996). Neural-fuzzy networks and phonetic feature recognition as a help for speechreading. In: Stork, D.G., Hennecke, M.E. (eds) Speechreading by Humans and Machines. NATO ASI Series, vol 150. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-13015-5_38
Download citation
DOI: https://doi.org/10.1007/978-3-662-13015-5_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08252-8
Online ISBN: 978-3-662-13015-5
eBook Packages: Springer Book Archive