- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
Using Genetic Algorithm To Determine The Architecture for Adaptive Neural Network To Recognize Some Of Arabic Phonemes | ||
| Journal of Basrah Researches (Sciences) | ||
| Article 1, Volume 34, Issue 2, 2008, Pages 7-14 PDF (0 K) | ||
| Author | ||
| Saba abdul w. Alabodey | ||
| Abstract | ||
| The aim of this paper is to determine the best architecture of neural network by using the genetic algorithm to recognize some of Arabic phonetics. In this paper the recorded speech signal has been processed through two stages. The first stage contains the required calculations of the best locations, while in the second stage the frequencies values and different manipulation have been calculated such as sorting, scaling and selecting three frequencies value to represent each phoneme. In the third stage the genetic algorithm will be used to determine the architecture of neural network to recognize the Arabic phonemes. The sound signals are recorded by using sound forge 5 , and work done by using Matlab 6.5 and turbopascal7 . As a result the recognition percentage is more than 80% . | ||
| Keywords | ||
| neural network; genetic algorithm; zero; Crossing; Fast Foruier Transform | ||
|
Statistics Article View: 199 PDF Download: 164 |
||