User Modeling and User-Adapted Interaction

, Volume 12, Issue 2, pp 111–137

Designing and Evaluating an Adaptive Spoken Dialogue System

  • Diane J. Litman
  • Shimei Pan
Article

DOI: 10.1023/A:1015036910358

Cite this article as:
Litman, D.J. & Pan, S. User Modeling and User-Adapted Interaction (2002) 12: 111. doi:10.1023/A:1015036910358

Abstract

Spoken dialogue system performance can vary widely for different users, as well for the same user during different dialogues. This paper presents the design and evaluation of an 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.

adaptive spoken dialogue systemshypothesis testing for the effectiveness of adaptationsPARADISE for evaluating performance measuresspeech recognitionuser model acquisition via machine learning

Copyright information

© Kluwer Academic Publishers 2002

Authors and Affiliations

  • Diane J. Litman
    • 1
  • Shimei Pan
    • 2
  1. 1.Computer Science Department and LRDCUniversity of PittsburghPittsburghUSA
  2. 2.IBM T.J. Watson Research CenterHawthorneUSA