—We propose an automatic approach to soft color segmentation, which produces soft color segments with an appropriate amount of overlapping and transparency essential to synthesiz...
A variational Bayesian framework is employed in the paper for image segmentation using color clustering. A Gaussian mixture model is used to represent color distributions. Variati...
In this work, musical instrument recognition is considered on solo music from real world performance. A large sound database is used that consists of musical phrases excerpted fro...
We present an approach to teach incrementally human gestures to a humanoid robot. The learning process consists of first projecting the movement data in a latent space and encodin...
This paper presents a novel training method of an eigenvoice Gaussian mixture model (EV-GMM) effectively using non-parallel data sets for many-to-many eigenvoice conversion, which...