Real-Time Visual Prosody for Interactive Virtual Agents
Speakers accompany their speech with incessant, subtle head movements. It is important to implement such “visual prosody” in virtual agents, not only to make their behavior more natural, but also because it has been shown to help listeners understand speech. We contribute a visual prosody model for interactive virtual agents that shall be capable of having live, non-scripted interactions with humans and thus have to use Text-To-Speech rather than recorded speech. We present our method for creating visual prosody online from continuous TTS output, and we report results from three crowdsourcing experiments carried out to see if and to what extent it can help in enhancing the interaction experience with an agent.
KeywordsVisual prosody Nonverbal behavior Realtime animation Interactive agents
We would like to thank Kirsten Bergmann and Philipp Kulms for their feedback on the design of the study and their help with the evaluation of the results. This work was partially performed within the Labex SMART (ANR-11-LABX-65) supported by French state funds managed by the ANR within the Investissements d’Avenir programme under reference ANR-11-IDEX-0004-02. It was also partially funded by the EU H2020 project ARIA-VALUSPA; and by the German Federal Ministry of Education and Research (BMBF) within the Leading-Edge Cluster Competition, managed by the Project Management Agency Karlsruhe (PTKA). The authors are responsible for the contents of this publication.
- 6.Eyben, F., Weninger, F., Gross, F., Schuller, B.: Recent developments in openSMILE, the Munich open-source multimedia feature extractor. In: Conference on Multimedia, pp. 835–838. ACM (2013)Google Scholar
- 8.Graf, H.P., Cosatto, E., Strom, V., Hang, F.J.: Visual prosody: facial movements accompanying speech. In: Automatic Face and Gesture Recognition, pp. 381–386. IEEE Computer Society (2002)Google Scholar
- 14.Levine, S., Theobalt, C., Koltun, V.: Real-time prosody-driven synthesis of body language. In: SIGGRAPH Asia, pp. 1–10. ACM, New York (2009)Google Scholar
- 17.van Welbergen, H., Yaghoubzadeh, R., Kopp, S.: AsapRealizer 2.0: the next steps in fluent behavior realization for ECAs. In: Bickmore, T., Marsella, S., Sidner, C. (eds.) IVA 2014. LNCS, vol. 8637, pp. 449–462. Springer, Heidelberg (2014) Google Scholar