- 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
Recognize some of Arabic phonemes by using Mamdani NeuroFuzzy Network | ||
| Journal of Al-Qadisiyah for Computer Science and Mathematics | ||
| Article 1, Volume 7, Issue 1, 2015, Pages 131-145 PDF (0 K) | ||
| Author | ||
| Saba Abdul-Wahed S | ||
| Abstract | ||
| Modified mamdani neurofuzzy network scheme has been proposed and presented in this paper to recognize some of Arabic phonemes. The number of connecting is reduced to be equal to the number of member ship function plus one. to training this network ,we used some of sound segments which contain from two or three phonemes and recorded from more than one person in different age and both sexes in the same environment by used the same recorded programming (sound forge 5.0) . The proposed technique has been testing by using different group from sound segments which recorded in the same environment and recorded program. The percentage of recognition reaches to 87% to all recorded phonemes | ||
| Keywords | ||
| Mamdani neurofuzzy; Adaptive back; propagation algorithm; zero crossing; speech recognizing | ||
|
Statistics Article View: 52 PDF Download: 34 |
||