Designing and Evaluating an Adaptive Spoken Dialogue System

Spoken dialogue systemperformance canvary widely fordifferentusers, aswell for the same userduring different dialogues.This paper presents the design and evaluation ofan adaptive version of TOOT, a spoken dialogue system for retrieving online train schedules. Based on rules learned from a set of training dialogues, adaptive TOOT constructs a user model representing whether the user is having speech recognition problems as a particular dialogue progresses. Adaptive TOOT then automatically adapts its dialogue strategies based on this dynamically changing user model. An empirical evaluation of the system demonstrates the utility of the approach. Key words. adaptive spoken dialogue systems, hypothesis testing for the e

• Type: Journal
• Year: 2002
• Where: UMUAI
• Authors: Diane J. Litman, Shimei Pan
• Keywords: Adaptive Toot, Dialogue, UMUAI 2002, User Model