OVERVIEW
Visual communications are spreading throughout the consumer market. We are quickly moving from a world dominated by telephone conversations to one in which fast, high-bandwidth connections will allow us to communicate with both audio and video in our daily interactions. Automated captioning would provide a powerful addition to this emerging technology.

Though captioning was designed to benefit hearing impaired communities, there are many other useful applications for captioning. Captioned text facilitates understanding of spoken words for all users. It is helpful in environments where audio is unavailable, audio quality is questionable, or multiple audio channels are in use simultaneously. Once generated, captioned discussions could be exported into a document to serve as minutes or facilitate key word searching. Finally, automated captioning in concert with other automated translation technologies would allow us to simultaneously display captions in multiple languages.

On the following pages we provide one viable example for each proposed model of integrated captioning. We discuss four hybridized models of existing technology, each building upon the last, to demonstrate that what we are proposing is, in fact, possible. For each model, we highlight potential applications of the system, outline the component technologies involved, and take the reader on a tour of the system architecture. There are clearly many paths on which future communications technology might evolve and several potential combinations. Were this system to become part of our daily lives, it is likely that it would consist of an integrated unit housed within a single box. Nonetheless, we will demonstrate that it is possible today to build a prototype of such a system out of existing communications technologies.

Back to Top

"InterCaption: Facilitating Communication Through Captioning"
© K. Acker, T. Lytle, J. Porvin (1998)
Back to VisCom 98 Projects Homepage