Advance Program - Tutorial

4. Designing Speech User Interfaces

Sunday, 08:30 - 17:00

Instructor
Jennifer Lai, IBM T.J. Watson Research Center, USA

Benefits
You will learn how to design an effective speech interface by understanding the challenges and benefits of using speech technology. You will also learn strategies for designing effective prompts, methods for handling user and system errors, as well as techniques for providing user feedback.

Origins
An updated version of a highly regarded CHI 99 and CHI 98 tutorial.

Features

• An introduction to the basic concepts of speech input (recognition) and output (synthesis)
• Examples of speech products and application areas
• Design issues that affect both multi-modal and speech-only systems including techniques for providing user feedback, strategies for designing effective prompts, methods for handling user and system errors
• User studies that are appropriate at different stages of a speech application's life cycle

Audience
Intended for user interface designers and application developers who are interested in understanding the issues involved in designing effective speech interfaces. No prior knowledge of speech input or output is assumed.

Presentation
This tutorial uses a combination of lecture and small group exercises. Examples of existing products and research prototypes, both live demonstrations and recorded audio and video, are used to illustrate system features and design techniques.

Instructor
Jennifer Lai is a Speech Interface designer at IBM Research. She has published papers on the use of speech in multi-modal systems and the development of statistical language models, and holds three patents in natural language translation.