A multitasking approach to adaptive spoken dialogue management

  • Authors:
  • Tobias Heinroth;Dan Denich;Wolfgang Minker

  • Affiliations:
  • Institute of Information Technology, Ulm University, Ulm, Germany;Institute of Information Technology, Ulm University, Ulm, Germany;Institute of Information Technology, Ulm University, Ulm, Germany

  • Venue:
  • UAHCI'11 Proceedings of the 6th international conference on Universal access in human-computer interaction: applications and services - Volume Part IV
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Undoubtedly one of the key factors of a computed world, are the interfaces users ought to use. In this paper we present the adaptive spoken dialogue manager OwlSpeak to provide a spoken interface to a computed world, in our case to an Intelligent Environment. The most important feature of the dialogue manager is its ability to pause, resume, and to switch between more than one interactive task, which is a prerequisite to provide adaptive spoken dialogues. Especially within Intelligent Environments it is necessary to modify the status of an interface depending on the changing contexts of the environment and on the actual requirements the user may have. We present the implementation and evaluation of OwlSpeak as part of an existing Intelligent Environment that can be used by real subjects and show how multitasking can be utilised to cope with an adaptive speech interface.