Abstract. Prosody has been actively studied as an important knowledge source for speech recognition and understanding. In this paper, we are concerned with the question of exploiti...
Given a large, real graph, how can we generate a synthetic graph that matches its properties, i.e., it has similar degree distribution, similar (small) diameter, similar spectrum,...
ing from Robot Sensor Data using Hidden Markov Models Laura Firoiu, Paul Cohen Computer Science Department, LGRC University of Massachusetts at Amherst, Box 34610 Amherst, MA 01003...
Protein fold recognition is a key step towards inferring the tertiary structures from amino-acid sequences. Complex folds such as those consisting of interacting structural repeat...
Semi-supervised learning (SSL), is classification where additional unlabeled data can be used to improve accuracy. Generative approaches are appealing in this situation, as a mode...