Wavelet and Neural Network Method for Speech Enhancement Objective Evaluation | ||||
The International Conference on Electrical Engineering | ||||
Article 90, Volume 7, 7th International Conference on Electrical Engineering ICEENG 2010, May 2010, Page 1-10 PDF (128.38 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/iceeng.2010.33258 | ||||
View on SCiNiTO | ||||
Authors | ||||
K. Daqrouq1; M. Alfaouri1; T. Abu Hilal2; J. O. Daqrouq3; S. El-Hajjar4 | ||||
1Electronic and Communication department-Philadelphia Univ.-Jordan. | ||||
2Arab Academy for Banking & Financial Sciences, Computer Information Systems. | ||||
3IT Department- Gazco Company-Abu Dhabi. | ||||
4Dhofar University, Foundation Department, Oman. | ||||
Abstract | ||||
Abstract: Wavelet Neural Network Evaluation method WNNEM is proposed as a powerful tool for enhanced speech signal evaluation. This objective evaluation measure utilizes Feed forward back Propagation Neural Network FFBNN to train the free of noise signal, and then enhanced signal is simulated to the training output results taken for given target. The distance between simulation and the target, over different wavelet sub bands is studied. Four known speech enhancement method for studying the performance of WNNEM are utilized. The advantage of this method is the evaluation of different band passes of frequency based on wavelet transform by neural network, which is very powerful classification tool. Several objective measures are used to investigate the WNNEM compatibility. Results proved the validity of the proposed method. | ||||
Keywords | ||||
Wavelets; Neural network; objective evaluation and speech enhancement | ||||
Statistics Article View: 94 PDF Download: 191 |
||||