| Paper: | SP-L2.5 | ||
| Session: | Modeling Approaches in Speaker Recognition | ||
| Time: | Wednesday, May 19, 10:50 - 11:10 | ||
| Presentation: | Lecture | ||
| Topic: | Speech Processing: Speaker Recognition | ||
| Title: | GENERALIZED LOCALLY RECURRENT PROBABILISTIC NEURAL NETWORKS FOR TEXT-INDEPENDENT SPEAKER VERIFICATION | ||
| Authors: | Todor Ganchev; University of Patras | ||
| Dimitris Tasoulis; University of Patras | |||
| Michael Vrahatis; University of Patras | |||
| Nikos Fakotakis; University of Patras | |||
| Abstract: | An extension of the well-known Probabilistic Neural Network(PNN), to Generalized Locally Recurrent PNN (GLRPNN) is introduced. This extension renders GLRPNNs, in contrast to PNNs, sensitive to the context, in which events occur. A GLRPNN is therefore, able to identify time or spatial correlations. This capability can be exploited to improve performance on classification tasks. A fast three-step algorithm for training GLRPNNs is also proposed. The first two steps are identical to the training of traditional PNNs, while the third step exploits the Differential Evolution optimization method. The performance of the proposed methodology on the task of text-independent speaker verification is contrastedwith that of Locally Recurrent PNNs, Diagonal Recurrent Neural Networks, Infinite Impulse Response and Finite Impulse Response MLP-based structures, as well as with Gaussian Mixture Models-based classifier. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops