Universiti Teknologi Malaysia Institutional Repository

Pengecaman sebutan digit menggunakan rangkaian neural : satu kajian terhadap carian bilangan nod. tersembunyi dan parameter pembelajaran.

Salam, Md. Sah and Mohamad, Dzulkifli and Sheikh Salleh, Sheikh Husain (2000) Pengecaman sebutan digit menggunakan rangkaian neural : satu kajian terhadap carian bilangan nod. tersembunyi dan parameter pembelajaran. Jurnal Teknologi Maklumat, 12 (2). pp. 36-54. ISSN 0128-3790

[img]
Preview
PDF
905Kb

Abstract

This research is about choosing suitable number of nodes in hidden layer and learning parameters in the proses of Malay number speech recognition system using neural network. The learning approach used in training Feed Forward Multilayer Perceptron (FFMLP) is back propagation. Speech for the study are analysed using Linear Predictive Coding (LPC) and Log Area Ratio (LAR) to represent speech signal for every 20ms. The neural network learning operation are greatly influenced by the parameters ie. momentum , learning rate and number of hidden nodes choosen. Choosing unsuitable parameters will make the neural network system give an answer divert from the desired one.

Item Type:Article
Uncontrolled Keywords:nodes, malay number speech recognition system, feed forward multilayer perceptron (FFMLP), linear predictive coding (LPC), log area ratio (LAR)
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System (Formerly known)
ID Code:8710
Deposited By: Ms Zalinda Shuratman
Deposited On:11 May 2009 00:41
Last Modified:02 Jun 2010 01:57

Repository Staff Only: item control page