Abstract. Application of neural networks for real world object recognition suffers from the need to acquire large quantities of labelled image data. We propose a solution that acq...
In many applications surfaces containing a large number of primitives occur. Geometry compression reduces storage space and transmission time for such models. A special case is gi...
Abstract. We propose a new method to generate unfolded area preserving representations of the cerebral cortex. The cortical surface is evolved with an application-specific normal m...
Jean-Philippe Pons, Renaud Keriven, Olivier D. Fau...
Abstract. A formal prosody model is proposed together with its application in a text-to-speech system. The model is based on a generative of abstract prosodic functionally involved...
We present a component for incremental speech synthesis (iSS) and a set of applications that demonstrate its capabilities. This component can be used to increase the responsivity ...