Title :
Comparative analysis of Serbian phonemes
Author :
Arsenijevic, Danijela ; Milosavljevic, Milan
Author_Institution :
Inst. of Appl. Math. & Electron., Belgrade, Serbia
Abstract :
2 autoregressive (AR) models of Serbian phonemes are examined in this paper. They are the linear autoregressive model and the nonlinear model realized in a feedforward neural network with one hidden layer. It is shown that both models gave satisfying results.
Keywords :
autoregressive processes; feedforward neural nets; multilayer perceptrons; speech processing; AR models; NNAR models; Serbian phonemes; comparative analysis; linear autoregressive model; nonlinear autoregressive models; one-hidden-layer feedforward neural network; Abstracts; Lips; Mathematical model; Mathematics; Natural languages; Neural networks; Pharynx; Speech analysis; Tongue; Transfer functions;
Conference_Titel :
Neural Network Applications in Electrical Engineering, 2002. NEUREL '02. 2002 6th Seminar on
Print_ISBN :
0-7803-7593-9
DOI :
10.1109/NEUREL.2002.1057971
