- 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
Arabic Numbers Sound Recognition | ||
| Tikrit Journal of Pure Science | ||
| Article 1, Volume 12, Issue 1, 2007, Pages 162-169 | ||
| Author | ||
| shahla Abd Al-Wahab | ||
| Abstract | ||
| In this research, dynamic time warping algorithm was used in the form of recognition Arabic sound numbers which is regarded one of the dynamic programming applications using the method of superimposition of the patterns capable of recognition the sounds of Arabic numbers through the search for best unique superimposition between the group elements of audio database of Arabic numbers . Two methods were used to analyze the voice signal. These are Mel-Frequency Cepstrum Coefficient (MFCC) and Linear Frequency Cepstrum Coefficient (LFCC) analyses. These two methods of analysis were compared and their effect on the final distinction process is shown. The program allows the testing of different sound numbers with analysis and dynamic time warping algorithm determinants to be inputs and the output is the number consistent with input with the determination of the speaker who spelled the number. Many experiments were held and also many tests to enhance the program performance. Training group included three speakers (a child, a female and a male) for audio database with different voices for training. The practical results proved the success of the method used in recognition. | ||
|
Statistics Article View: 177 PDF Download: 46 |
||