Deep Learning has been applied successfully to speech processing. In this paper we propose an architecture for speech synthesis using multiple speakers. Some hidden layers are shared by all the speakers, while there is a specific output layer for each speaker. Objective and perceptual experiments prove that this scheme produces much better results in comparison with single speaker model. Moreov...

The results of a recent study have provided direct support for the suggestion that conditional learning in rats is best characterized by a 3-layer connectionist network (M. J. Allman, J. Ward-Robinson, & R. C. Honey, 2004). In the 2 experiments reported here, rats were used to investigate the nature of the changes that occur when a stimulus compound is presented, whose components activate hidde...

The following report presents the preliminary results and theoretical backgrounds of a multi-layer evolutionary mechanism. The project aims at developing a mechanism for automated agent design within a pre-designed multi-layer architecture. The core mechanism used in the experiments is a Genetic Programming algorithm working in a specially designed condition-action rules system. Described multi...

This paper proposes a general associative memory (GAM) system that combines the functions of other typical associative memory (AM) systems. The GAM is a network consisting of three layers: an input layer, a memory layer, and an associative layer. The input layer accepts key vectors, response vectors, and the associative relationships between these vectors. The memory layer stores the input vect...

[1] In a series of numerical experiments, arrays of parallel-dipping normal faults formed only if the model contained a thin viscous layer sandwiched between the brittle, faulted layer on top and a lower boundary that resisted vertical displacement. With this particular vertical stratification, parallel-dipping faults developed even if the viscous layer had a shear-stress-free lower boundary co...

This paper discusses the use of Box Behnken design (BBD) approach to plan the experiments for turning the yield of CVD, thickness and layer number of graphene sheets with an overall objective of optimizing the process to provide higher graphene production volume, fewer layers and thinness structure of graphene. BBD is having the maximum efficiency for an experiment involving four factors such a...

A series of reverse osmosis (RO) membrane filtration experiments was performed systematically in order to investigate the effects of various hydrodynamic and physicochemical operational parameters on a cake layer formation in colloidal and particulate suspensions. Bench-scale fouling experiments with a thin-film composite RO membrane were performed at various combinations of trans-membrane pres...

This paper discusses the use of Box Behnken design (BBD) approach to plan the experiments for turning the yield of CVD, thickness and layer number of graphene sheets with an overall objective of optimizing the process to provide higher graphene production volume, fewer layers and thinness structure of graphene. BBD is having the maximum efficiency for an experiment involving four factors such a...