Tarbiat Modares University The Modares Journal of Electrical Engineering 2228-527X 10 3 2010 10 01 Speech Enhancement Based on Spectral Subtraction and Genetic Programming بهسازی گفتار مبتنی بر روش ترکیبی تفاضل طیفی و برنامه‌نویسی ژنتیک 21 36 12814 EN Saeideh Sadat Sadidpour AmirKabir University of Technology Mohammad Mahdi Homayounpour AmirKabir University of Technology Mahdi Fasanghari Iran Telecommunication Research Center Journal Article In this paper, genetic programming is applied for quality improvement of noisy speech signal. Therefore, a system including both spectral subtraction and genetic programming is implemented for speech enhancement. In the proposed method, first noise is reduced by spectral subtraction. In the next step, genetic programming trees are trained for more enhancement of noisy signal by mapping the signal obtained by spectral subtraction to clean data. The proposed hybrid method improves signal to noise ratio about 2 to 6.5 dB. Comparison of genetic programming, multi-layer perceptron neural network, spectral subtraction, and the proposed hybrid method for speech enhancement indicates that the combination of spectral subtraction and genetic programming presents much better quality for enhanced signal compared to the other methods studied in this paper. https://mjee.modares.ac.ir/article_12814_d46e6e59cb2e09d436f89c57efa23735.pdf