Please use this identifier to cite or link to this item:
Title: Radial basis function neutral networks for speaker verification
Authors: Li, Guojie
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
DRNTU::Engineering::Computer science and engineering::Computing methodologies
Issue Date: 2005
Source: Li, G. (2005). Radial basis function neutral networks for speaker verification. Master’s thesis, Nanyang Technological University, Singapore.
Abstract: This thesis presents the application of a minimal radial basis function (RBF) neural network, referred to as MRAN (Minimal Resource Allocation Network) for speaker verification. Extension of MRAN to elliptical basis functions has been studied too. MRAN is a sequential learning algorithm for radial basis function neural networks. During the training, MRAN allows hidden neurons to be added or removed thus to realize a minimal network. MRAN recruits hidden neurons based on the novelty of the input data. If all of the novelty criteria can not be satisfied, the existing network parameters are updated by extended Kalman filter (EKF). Additionally, MRAN’s pruning strategy removes hidden neurons from the network if their contributed output to the output layer is insignificant. In this way, MRAN is adapted to fit the dynamics of the input data closely.
DOI: 10.32657/10356/4626
Rights: Nanyang Technological University
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
EEE-THESES_641.pdf2.47 MBAdobe PDFThumbnail

Page view(s) 20

Updated on Nov 26, 2020

Download(s) 20

Updated on Nov 26, 2020

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.