Blind Source Separation of musical instrument signals by identification of wavelets and filter bank coefficients

This paper, presents a new approach in Blind Source Separation (BSS) using identified wavelets in musical instruments as window function in the Degenerate Unmixing Estimation Technique (DUET) algorithm. the scaling function and the wavelet functions of the wavelets present in musical instruments, violin and flute is presented. NLMS algorithm is used to identify the filter bank coefficients of wavelet-like elements, found repeating in musical notes of the instruments. Scaling functions of the standard wavelets are also found out by an iterative manner using NLMS algorithm. wavelets for different musical instruments are developed. The obtained wavelets are utilized in the DUET algorithm to achieve the goal of BSS to the mixed source of music instruments signals.