Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Detecting Certainness in Spoken Tutorial Dialogues

Jackson Liscombe, Julia Hirschberg, Jennifer J. Venditti

Columbia University, USA

What role does affect play in spoken tutorial systems and is it automatically detectable? We investigated the classification of student certainness in a corpus collected for ITSPOKE, a speechenabled Intelligent Tutorial System (ITS). Our study suggests that tutors respond to indications of student uncertainty differently from student certainty. Results of machine learning experiments indicate that acoustic-prosodic features can distinguish student certainness from other student states. A combination of acousticprosodic features extracted at two levels of intonational analysis - breath groups and turns - achieves 76.42% classification accuracy, a 15.8% relative improvement over baseline performance. Our results suggest that student certainness can be automatically detected and utilized to create better spoke dialog ITSs.

Full Paper

Bibliographic reference.  Liscombe, Jackson / Hirschberg, Julia / Venditti, Jennifer J. (2005): "Detecting certainness in spoken tutorial dialogues", In INTERSPEECH-2005, 1837-1840.