Speech Enhancement Based on Spectral Subtraction and Genetic Programming

	Speech Enhancement Based on Spectral Subtraction and Genetic Programming
The Modares Journal of Electrical Engineering
Article 2, Volume 10, Issue 3, 2010, Pages 21-36 PDF (1.14 M)
Authors
saeideh sadat Sadidpour¹; mohammad mahdi Homayounpour^* ¹; mahdi Fasanghari²
¹AmirKabir University of Technology
²Iran Telecommunication Research Center
Abstract
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.
Keywords
Genetic programming; Spectral Subtraction; Noisy Speech; Speech Enhancement
Statistics Article View: 122 PDF Download: 75