Using Speech to Facilitate the Education Process

Maxine Cohen

Nova Southeastern University
cohenm@scis.acast.nova.edu

CHI '97 Workshop: Speech User Interface Design Challenges

Short Biography

Maxine Cohen is Assistant Professor at Nova Southeastern University in Ft. Lauderdale. She teaches courses in Human-Computer Interaction, Multimedia and Emerging Technologies and Applications on the Internet. Prior to joining Nova, she worked at IBM in Boca Raton, where she was responsible for the user interface design and testing of their mobile, voice and pen products. Before joining IBM, she taught at the State University of New York at Binghamton. Last year, she participated in the CHI 96 Workshop on Speech Recognition. She has been accepted as a SIG co-organizer for a session on HCI Education at CHI 97. She has served as a reviewer for the CHI 96 and CHI 97 paper sessions. She also reviewed papers for the Transactions on Computer Human Interaction (TOCHI) special edition on speech interfaces. She serves as category editor for Information Interfaces and Presentation for ACM Computing Reviews.

Position Paper

The future of educational delivery systems is changing from face-to-face traditional classroom situations to on-line distance learning environments. At the same time, computers are an integral part of this on-line learning phenomenon supplying the interface and connection between student and teacher.

For the last year, I have been working in this on-line environment teaching at Nova Southeastern University. One of the problems I face is how to effectively communicate with my students and try to make the on-line learning environment as effective as possible. I believe integrating the use of speech technology into this environment will help on many levels.

Quite a bit of my time is spent in grading assignments submitted through our on-line facilities. I find I still need to print out the assignments and grade their hard copy versions. Then in a traditional classroom setting, I would return to class the next week and turn the assignments back to the students with my comments. In an on-line environment this won't work, since there's no easy way to return the assignments in their hard copy format. (They could be mailed or faxed, but then it looks too much like a correspondence school, not an interactive on-line environment.) So in my on-line environment I compose a mail message and with the aid of a grading template, type in my handwritten notes and comments. I find, even with the template, it still can take as long to type in the responses as it did to originally grade the assignment. Thereby, just about doubling my time.

What I would like to propose is to use a speech system to dictate the comments on the assignment and send that to the students. There are several approaches to this scenario. Should the results just be dictated and converted to text that the students can continue to read as an email like message? Should the results remain a voice file that in a multimedia environment students can play back (even repeatedly) and hear the professor's voice? Personally, I find the second choice more exciting and adding a real dimension to the on-line environment. But this involves lots of storage and additional hardware.

What I would like to see discussed at this workshop:

As more and more institutions turn to on-line teaching environments, this not only will save the instructor time, but bring an added dimension and additional reality to the on-line learning experience.

Reference

Hiltz, Starr Roxanne. (1994). The virtual classroom : learning without limits via computer networks. Ablex Publishing Corporation: Norwood, N.J.

CHI '97 Workshop: Speech User Interface Design Challenges