Synthesizing multimodal utterances for conversational agents

By Stefan Kopp, Ipke Wachsmuth. Comput. Animat. Virtual Worlds, 2004

302 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

To Err is Human(-like): Effects of Robot Gesture on Perceived Anthropomorphism and Likability (2013, background): “Based on the deﬁnition provided in [12], each chunk refers to a single idea unit represented by an intonation phrase and, optionally in a multimodal utterance, by an additional co-expressive gesture phrase.”
Towards a Common Framework for Multimodal Generation: The Behavior Markup Language (2006, methodology): “As we have already mentioned, the Behavior Markup Language presented here is an improvement and extension of prior related languages that have been used extensively in many projects [2, 3, 4, 7, 9, 11, 12, 17, 20].”
Gesture-based Object Recognition using Histograms of Guiding Strokes (2012, methodology): “For a similar segmentation, we apply the concept of guiding strokes, proposed by Kopp and Wachsmuth [5], which splits gestural wrists’ trajectories with respect to their spatial and kinematic features.”
SmartBody: behavior realization for embodied conversational agents (2008, methodology): “The specific problem of synthesizing realistic behaviors for conversational characters has been also addressed by several researchers [26, 27, 28, 29].”