Generating Verbal and Nonverbal Utterances for Virtual Characters
We introduce an approach to multimodal generation of verbal and nonverbal contributions for virtual characters in a multiparty dialogue scenario. This approach addresses issues of turn-taking, is able to synchronize the different modalities in real-time, and supports fixed utterances as well as utterances that are assembled by a full-fledged tree-based text generation algorithm. The system is implemented in a first version as part of the second VirtualHuman demonstrator.
Unable to display preview. Download preview PDF.
- 1.Becker, T.: Natural Language Generation with Fully Specified Templates. In: Wahlster, W. (ed.) SmartKom: Foundations of Multimodal Dialogue Systems. Springer, Heidelberg (2006)Google Scholar
- 2.Engel, R.: SPIN: Language Understanding for Spoken Dialogue Systems Using a Production System Approach. In: Proc. of 7th ICSLP, Denver (2002)Google Scholar
- 3.Kempe, B.: PATE - a Production Rule System based on Activation and Typed Feature Structure Elements, Bachelor Thesis, Saarland University, Saarbrücken (2004)Google Scholar
- 5.Pfleger, N.: FADE - An Integrated Approach to Multimodal Fusion and Discourse Processing. To appear in Proceedings of the Doctoral Spotlight Session of ICMI (2005)Google Scholar