TIDE supports usability engineering, evaluation and monitoring of spoken dialogue applications

Motivation & Project Description

• Implement an automatic testbed as an efficient tool for usability engineering, evaluation and monitoring of speech-based dialogue services.
• Usability is predicted in two steps:
  • Quantify the interaction between user and system in a parametric way.
  • Use parameters to predict usability, user satisfaction or acceptability – without directly asking the user!

   

Outcome:

• Testbed for predicting usability on speech-based dialogue platforms, including:

  • Algorithms for extracting parameters from the audio signals (signal level).

  • Algorithms for extracting parameters from the speech recognition hypothesis and from other logged information (symbolic level).

  • Usability prediction algorithms.

Time Frame:  07/2006 - 03/2007

T-labs Team Members:S. Möller, J. Ajmera, K.-P. Engelbrecht, F. Metze

Students: N. Fecher

Partners: Forschungszentrum Telekommunikation Wien (ftw), Christian-Albrechts-Universität zu Kiel

Funding by: Deutsche Telekom Laboratories