This paper presents a novel application of speech emotion recognition: estimation of the level of conversational engagement between users of a voice communication system. We begin...
We introduce a novel framework for simultaneous structure and parameter learning in hidden-variable conditional probability models, based on an entropic prior and a solution for i...
Recurrent neural networks serve as black-box models for nonlinear dynamical systems identification and time series prediction. Training of recurrent networks typically minimizes t...
The JavaPorts system is an environment that facilitates the rapid development of modular, reusable, Java-based parallel and distributed applications for networked machines with het...
Abstract. Reservoir computing approaches have been successfully applied to a variety of tasks. An inherent problem of these approaches, is, however, their variation in performance ...