Abstract
Can speaker gaze and speaker arm movements be used as a practical information source for naturalistic conversational human–computer interfaces? To investigate this question, we recorded (with eye tracking and motion capture) a corpus of interactions with a (wizarded) system. In this paper, we describe the recording, analysis infrastructure that we built for such studies, and analysis we performed on these data. We find that with some initial calibration, a “minimally invasive”, stationary camera-based setting provides data of sufficient quality to support interaction.
Original language | American English |
---|---|
Title of host publication | Proceedings of the SIGDIAL 2013 Conference |
State | Published - 2013 |
Externally published | Yes |
EGS Disciplines
- Computer Sciences