This lecture concerns the state-of-the-art in the research community in developing computer conversational systems that are typically able to provide access to on-line information sources through natural spoken dialogue interaction. Some of the existing domains include weather information, flight status and schedules, a restaurant and hotel guide, navigation assistance, and traffic status. Such systems are typically configured as a suite of servers, each of which specializes in one aspect of the problem, such as speech recognition, language understanding, discourse and dialogue modeling, database retrieval, response planning, language generation, and speech synthesis. A significant portion of the lecture will be devoted to the dialogue interaction component, which is typically very difficult to build and requires a great deal of effort. Since speech recognition is error-prone, systems must be able to recognize potential misunderstandings and respond in ways that can lead to an efficient resolution of the user's intended task. In addition, an important research issue is how to configure systems that will enable rapid porting to new domains and languages. The lecture will be augmented with several video and audio clips to help illustrate typical systems.

Stephanie Seneff is a Principal Research Scientist in the Spoken Language Systems Group at the MIT Laboratory for Computer Science. She received the B.S. degree in Biophysics from MIT in 1968, the M.S. and E.E. degrees in Electrical Engineering and Computer Science in 1980, and the PhD degree in EECS in 1985, also from MIT. Her current research interests encompass many aspects of the development of computer conversational systems, including speech recognition, probabilistic natural language parsing, discourse and dialogue modelling, speech generation, and integration between speech and natural language. She has published extensively on these topics, and has supervised many student theses at MIT, several at the Doctoral level. She played a leadership role in the develoment of the Galaxy architecture for spoken dialogue systems, which is widely used in the research community. She has served on the Speech Technical Committee for the IEEE Society for Acoustics, Speech and Signal Processing, and is a member of the Editorial Board for the Speech Communications journal. She has also served as a member of the Permanent Council for the International Conference on Spoken Language Systems (ICSLP).