Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
In this paper we proposed some flexible methods, which are useful in the process of voice conversion. The proposed methods modify the shape of the vocal tract system and the chara...
Abstract. The aim of this paper is to try to understand the structure of time in information technologies. Starting with historical arguments, it first shows that time is neither l...
Many time series exhibit dynamics over vastly different time scales. The standard way to capture this behavior is to assume that the slow dynamics are a “trend”, to de-trend t...
This paper makes the case that pin bandwidth will be a critical consideration for future microprocessors. We show that many of the techniques used to tolerate growing memory laten...