2002 Conference Proceedings

Go to previous article 
Go to next article 
Return to 2002 Table of Contents


VOICE RECOGNITION TECHNOLOGY FOR INSTANT CAPTIONING: PART IV. NEW AND EXTENDED APPLICATIONS

Dr. Robert H. Paine
Department of Chemistry
College of Science
Rochester Institute of Technology
85 Lomb Memorial Drive
Rochester, NY 14623
rhpsch@rit.edu 
Phone: 716-475-2516
Fax: 716-475-7800

This paper presents the further work of the author and his co-inventors, on Voice Recognition Technology for Instant Captioning. Initially, this work was directed toward captioning tapes for distance-learning (DL) Chemistry Courses. The original work was funded by grants from the Dodge Foundation, as well as the Camille and Henry Dreyfus Foundation, Inc for the Advancement of the Chemical Sciences, as well as funds from the Rochester Institute of Technology (RIT).

Distance Learning, now evolving into on-line (OL) learning, has been in vogue at RIT since 1978. Chemistry efforts began in 1992, and there are now some fifteen chemistry & Biochemistry courses now available via DL/OL.

RIT is also the home for the National Technical Institute for the Deaf (NTID). It is not a surprise that some of these students might enroll in a DL/OL chemistry course. Because of this, it was soon obvious that the videotapes, the most popular form for offering DL lectures, would need to be captioned for the hearing-impaired. The variety of methods then available for captioning were tedious, expensive, and required great precision. There was a time long before the students could obtain the lecture tapes. It was quickly realized that if Voice Recognition Technology (VRT) could be used, many of the following advantages would be realized:

1. Early availability.
2. An accurate rendition of the speakers words.
3. An economic savings.

Research began on this project five years ago to assist the hearing-impaired. It was soon apparent that the benefits were applicable audience

1. Hearing Impaired Students.
2. Students with dyslexia.
3. Students with various learning disabilities.
4. Students for whom English is a second language.
5. Students who employ mountain-goat thinking.
6. Students in noisy environments.

As this work proceeded, strong pedagogic synergism produced by the instant captioning was apparent in the entire audience viewing the chemistry videotapes.

This allowed the work to proceed at a significant pace, achieving a degree of success in 1999 that was reported earlier (reference to part 1,2,3)

Once the VR captioning reached a reasonably high quality of reproduction, the inventors submitted a patent (pending) on these discoveries. Licensing considerations may be discussed with the author.

The ensuing work on the VR captioning is now in pursuit of the following landmarks.

1- Mobility. Heretofore, the entire system was hardwired to a reasonably large permanent set up. Recent work has been completed so that the VR captioning system is installed on a cart that can be moved from classroom to classroom, for use in several (many) courses.
2- Reduction in size. Work is underway to make the entire system no larger than a brief case, facilitating movement from institution to institution. This work is about fifty percent complete.
3- Development of software/hardware that will incorporate into a lap-top computer, so that any as hoc lecture may provide through a compatible TV Projection system, instant captioning.

All three of these later objectives, as well as the original captioning objective, are most effective, since they all generate a presentation system, where the viewer need only look in on direction to receive all the information.

All new achievements and problems will be discussed in this presentation.

References

1. Voice Recognition Technology: A Strong Synergism (Technology and Disabled Persons Conference, March 1999)

2. Voice Recognition Technology: Part 2. A More Complete Story (Technology abd Disabled Persons Conference, March 2000)

3. Voice Recognition Technology: Part 3.New Experiences and Revelations (Technology and Disabled Persons Conference, March 2001)


Go to previous article 
Go to next article 
Return to 2002 Table of Contents 
Return to Table of Proceedings


Reprinted with author(s) permission. Author(s) retain copyright.