Audio Melody Extraction from Monophonic Turkish Maqam Music

Abstract

In this study, a new method is proposed for predominant audio melody extraction in monophonic Turkish maqam music works. The music signals are decomposed using the Improved Variable Mode Decomposition Method and the fundamental frequencies are obtained by calculation of center frequencies on each mode. In order to estimate and selection of predominant melody line some parameters are determined from the different number of frequency information in each window. The obtained results are compared to YIN and MELODIA which are the signal processing algorithms used for western music. MIREX criterias are used in the evaluation step, adhering to international standards. Simulation results have shown that Improved Variable Mode Decomposition Method gives more successful results than other methods used in comparison.