—In this paper, we propose a circular blurred shape model descriptor to deal with the problem of symbol detection and classification as a particular case of object recognition. ...
—Many complex dynamical phenomena can be effectively modeled by a system that switches among a set of conditionally linear dynamical modes. We consider two such models: the switc...
Emily B. Fox, Erik B. Sudderth, Michael I. Jordan,...
Our goal is to automatically learn a perceptually-optimal target cost function for a unit selection speech synthesiser. The approach we take here is to train a classifier on human...
Traditional classification methods assume that the training and the test data arise from the same underlying distribution. However, in several adversarial settings, the test set is...
In this paper, we describe a novel speaker adaptation algorithm based on Gaussian mixture weight adaptation. A small number of latent speaker vectors are estimated with non-negati...