Abstract
To gain insight into gaze behavior in meetings, this paper compares the results from a Naive Bayes classifier, Neural Networks and humans on speaker prediction in four-person meetings given solely the azimuth head angles. The Naive Bayes classifier scored 69.4% correctly, Neural Networks 62.3% and humans only 37.7%. None of the classifiers was able to generalize over meetings. We show that there are strong indications that human specific gaze behavior influences the fact that the models do not generalize. Additionally, we show that for all classifiers the performance of the prediction in the beginning and at the end of a speaker turn is worse than halfway through the speaker turn.
Original language | Undefined |
---|---|
Title of host publication | Proceedings of the Fourteenth Annual Machine Learning Conference of Belgium and the Netherlands (Benelearn 2005) |
Editors | M. van Otterlo, Mannes Poel, M. Poel, A. Nijholt, Antinus Nijholt |
Place of Publication | Enschede |
Publisher | University of Twente |
Pages | 73-79 |
Number of pages | 7 |
Publication status | Published - 2005 |
Event | 14th Belgium-Dutch Conference on Machine Learning, Benelearn 2005 - Enschede, the Netherlands, Bruges, Belgium Duration: 27 Apr 2005 → 29 Apr 2005 Conference number: 14 |
Publication series
Name | CTIT Workshop Proceedings Series |
---|---|
Publisher | University of Twente |
Volume | WP05-03 |
ISSN (Print) | 1574-0846 |
Conference
Conference | 14th Belgium-Dutch Conference on Machine Learning, Benelearn 2005 |
---|---|
Abbreviated title | Benelearn 2005 |
Country/Territory | Belgium |
City | Bruges |
Period | 27/04/05 → 29/04/05 |
Other | February 17-18, 2005 |
Keywords
- EWI-1815
- METIS-227355
- IR-65556
- EC Grant Agreement nr.: FP6/506811