![]() |
MIT Electrical Engineering and Computer Science
EECS Event |
Monday, November 26, 2001
4:00 PM (refreshments 3:45)
Edgerton Hall, Room 34-101
EECS Colloquium
Abstract
Successful navigation on the information highway depends crucially on our ability to provide an intuitive user interface, so that ordinary citizens can access, process, and manipulate vast amounts of information for work, learning, and play. A speech interface, in the user's natural language, is highly desirable because it is the most natural, flexible, efficient, and economical form of human communication.
We are witnessing the emergence of the first generation of speech-based interfaces. These systems rely primarily on speech recognition technologies either to help users prepare documents or conduct limited telephone-based transactions. However, many tasks that lend themselves to spoken input - making travel arrangements, for example, or selecting a movie/restaurant - are highly interactive. The solution is often built up incrementally, with both the user and the computer playing active roles. In this case, several human language technologies must be developed and integrated to reach this goal.
In this talk, I will describe the next generation of interfaces, namely interfaces that will act as our conversational partner to access information and solve problems, discuss the necessary technologies that will bring them into reality, and demonstrate some of the technologies and systems currently being developed at the MIT Laboratory for Computer Science.