Melody Extraction from Polyphonic Audio Signal Mirex2011

This paper considers the proposed algorithm submitted to theMusic Information Retrieval Evaluation eXchange(MIREX) 2011 “AudioMelody Extraction” task. The proposed melody pitch extraction algorithm can be divided into three steps: (1) a spectral analysis using variable length window, (2) a pitch candidate estimation, and (3) a pitch sequence identification. In the first step, the short-time Fourier transform (STFT) with variable length window is performed to be robust against dynamic variation of melody line. In the second step, melody pitch candidates of each frame are obtained from weights of a harmonic structure in the spectrum. In the third step, a single pitch sequence (melody line) is selected from the many possible pitch sequences based on the general properties of melody line.