Generalized locally recurrent probabilistic neural networks with application to text-independent speaker verification

Authors:
Todor D. Ganchev;Dimitris K. Tasoulis;Michael N. Vrahatis;Nikos D. Fakotakis
Affiliations:
Wire Communications Laboratory, Department of Electrical and Computer Engineering, University of Patras, GR-26500 Rion-Patras, Greece;Computational Intelligence Laboratory, Department of Mathematics, University of Patras, GR-26500 Rion-Patras, Greece;Computational Intelligence Laboratory, Department of Mathematics, University of Patras, GR-26500 Rion-Patras, Greece;Wire Communications Laboratory, Department of Electrical and Computer Engineering, University of Patras, GR-26500 Rion-Patras, Greece
Venue:
Neurocomputing
Year:
2007

Citing 10
Cited 7

Probabilistic neural networks

Neural Networks
Practical neural network recipes in C++

Practical neural network recipes in C++
Robust maximum likelihood training of heteroscedastic probabilistic neural networks

Neural Networks
POLYCOST: A telephone-speech database for speaker recognition

Speech Communication - Speaker recognition and its commercial and forensic applications
Differential Evolution – A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces

Journal of Global Optimization
Fir and iir synapses, a new neural network architecture for time series modeling

Neural Computation
On-line learning algorithms for locally recurrent neural networks

IEEE Transactions on Neural Networks
Temporal updating scheme for probabilistic neural network with application to satellite cloud classification

IEEE Transactions on Neural Networks
A general regression neural network

IEEE Transactions on Neural Networks
Diagonal recurrent neural networks for dynamic systems control

IEEE Transactions on Neural Networks

Novel Approaches to Probabilistic Neural Networks Through Bagging and Evolutionary Estimating of Prior Probabilities

Neural Processing Letters
Fuzzy Evolutionary Probabilistic Neural Networks

ANNPR '08 Proceedings of the 3rd IAPR workshop on Artificial Neural Networks in Pattern Recognition
Permanent oscillations in a 3-node recurrent neural network model

Neurocomputing
Learning in fully recurrent neural networks by approaching tangent planes to constraint surfaces

Neural Networks
Power quality disturbances classification based on S-transform and probabilistic neural network

Neurocomputing
Average framing linear prediction coding with wavelet transform for text-independent speaker identification system

Computers and Electrical Engineering
Neural network and wavelet average framing percentage energy for atrial fibrillation classification

Computer Methods and Programs in Biomedicine

Quantified Score

Hi-index	0.01

Visualization

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.