A recurrent fuzzy neural network for adaptive speech prediction

Author

Stavrakoudis, D.G. ; Theocharis, J.B.

Author_Institution

Aristotle Univ. of Thessaloniki, Thessaloniki

fYear

2007

fDate

7-10 Oct. 2007

Firstpage

2056

Lastpage

2061

Abstract

An enhanced memory TSK-type fuzzy neural network (EM-TRFN) is proposed in this paper, suitable for nonlinear adaptive speech prediction. The feedback links of the network are realized through finite impulse response (FIR) synapses, increasing the depth of the time-series history the network processes. The EM-TRFN is evolved in an on-line manner, with concurrent structure and parameter learning. Simulations on a speech signal prediction problem illustrate the effectiveness of the proposed network, provided by its enhanced temporal capabilities, in grasping the complex dynamic of the speech signal.

Keywords

adaptive signal processing; fuzzy neural nets; recurrent neural nets; speech processing; time series; feedback links; finite impulse response synapses; nonlinear adaptive speech prediction; parameter learning; recurrent fuzzy neural network; time-series history; Adaptive systems; Finite impulse response filter; Fuzzy neural networks; Fuzzy reasoning; Fuzzy systems; Inference algorithms; Inference mechanisms; Neurofeedback; Predictive models; Speech enhancement; dynamic fuzzy reasoning; ordered derivative; recurrent fuzzy neural networks; speech signal prediction;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2007. ISIC. IEEE International Conference on

Conference_Location

Montreal, Que.

Print_ISBN

978-1-4244-0990-7

Electronic_ISBN

978-1-4244-0991-4

Type

conf

DOI

10.1109/ICSMC.2007.4414191

Filename

4414191