Perception of Visual Scene and Intonation Patterns of Robot Utterances

Ivana Kruijff-Korbayová, Raveesh Meena, Pirita Pyykkönen

In: Proceedings of the 6th ACM/IEEE International Conference on Human-Robot Interaction. ACM/IEEE International Conference on Human-Robot Interaction (HRI) 6th March 6-9 Lausanne Switzerland ACM 2011.


It is established that assigning intonation to dialogue system output in a way that reflects relationships between entities in the discourse context can enhance the acceptability of system utterances. Previous research has concentrated on the role of linguistic context in processing; dialogue situatedness and hence the role of visual context in determining accent placement has not been studied. In this paper, we present an experimental study addressing the influence of visual context on the perception of nuclear accent placement in synthesized clarification requests. We found that utterances with nuclear accent placement licensed by the visual scene are perceived as appropriate more often then utterances with nuclear accent placement not licensed by the visual scene.


final.hri.intonation.pdf (pdf, 543 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence