Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

New Feature Parameters for Detecting Misunderstandings in a Spoken Dialogue System

Jun-Ichi Hirasawa, Noboru Miyazaki, Mikio Nakano, Kiyoaki Aikawa

NTT Laboratories, Atsugi, Kanagawa, Japan

This paper describes new feature parameters for detecting misunderstandings in a spoken dialogue system. Although recognition errors cannot be completely avoided with current speech recognition techniques, a spoken dialogue system could be a good human-machine interface if it could automatically detect and recover from its own misunderstandings during natural interaction between it and a user. For this purpose, we collected user responses to system confirmations with/without the system misunderstandings using the wizard of OZ method so that we could analyze the differences in the characteristics of user responses following correct/incorrect confirmations. The experimental results demonstrate that the content and duration of the user responses are good feature parameters for detecting the system's misunderstandings.


Full Paper

Bibliographic reference.  Hirasawa, Jun-Ichi / Miyazaki, Noboru / Nakano, Mikio / Aikawa, Kiyoaki (2000): "New feature parameters for detecting misunderstandings in a spoken dialogue system", In ICSLP-2000, vol.2, 154-157.