- 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
Identification of Noisy Arabic Speech Utterance using Multiwavelet Compression | ||
| Diyala Journal For Pure Science | ||
| Article 1, Volume 6, Issue 1, 2010, Pages 1-15 | ||
| Author | ||
| Taha Mohammed Hasan | ||
| Abstract | ||
| This paper presents a method that uses the multiwavelet transform in compressing a noisy speech signal and then, testing its effect on the reconstruction of noisy speech utterances after decompression. The ability of multiwavelet transform in compacting signal energy is employed to separate the significant signal features from the noise contribution. The proposed technique showed an improved SNR for the processed speech samples. In each performed experiment, the correlation coefficients are computed and compared to the correlation coefficient yielded by a similar compression scheme based on the cosine transform. The use of the multiwavelet based compression technique is superior in identification of noisy Arabic speech utterance especially at high input SNR values. | ||
| Keywords | ||
| speech Compression; multiwavelet Transform; Pattern Recognition | ||
|
Statistics Article View: 22 PDF Download: 3 |
||