Towards an Architecture for Aligned Speech and Gesture Production

  • Authors:

  • Stefan Kopp;Kirsten Bergmann

  • Affiliations:

  • Artificial Intelligence Group, University of Bielefeld, P.O. Box 100131, 33501 Bielefeld, Germany;Artificial Intelligence Group, University of Bielefeld, P.O. Box 100131, 33501 Bielefeld, Germany

  • Venue:
  • IVA '07 Proceedings of the 7th international conference on Intelligent Virtual Agents
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

The automatic production of speech and gesture is one of the most challenging issues in building embodied conversational agents, due to the intricacy of how the two modalities seem to "align" with each other. Based on experiences from computational approaches and inspired by current theoretical modeling attempts, we propose an architecture to simulate how on-the-spot speech and gesture production might run and bring about more natural multimodal behavior.