Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
408605 | Neurocomputing | 2007 | 15 Pages |
Abstract
An extension of the well-known probabilistic neural network (PNN) to generalized locally recurrent PNN (GLR PNN) is introduced. The GLR PNN is derived from the original PNN by incorporating a fully connected recurrent layer between the pattern and output layers. This extension renders GLR PNN sensitive to the context in which events occur, and therefore, capable of identifying temporal and spatial correlations. In the present work, this capability is exploited to improve the speaker verification performance. A fast three-step method for training GLR PNNs is proposed. The first two steps are identical to the training of original PNNs, while the third step is based on the differential evolution (DE) optimization method.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Todor D. Ganchev, Dimitris K. Tasoulis, Michael N. Vrahatis, Nikos D. Fakotakis,