Source Separation and Analysis of Piano Music Signals Using Instrument-Specific Sinusoidal Model
Many existing monaural source separation systems use sinusoidal modeling to represent pitched musical sounds during the separation process. In these sinusoidal modeling systems, a musical sound is represented by a sum of time-varying sinusoidal components, and the goal of source separation is to estimate the parameters of each component. Here, we propose an instrument-specific sinusoidal model tailored for a piano tone. Based on our proposed Piano Model, we develop a monaural source separation system to extract each individual tone from mixture signals of piano tones and at the same time, to identify the intensity and adjust the onset of each tone for characterizing the nuance of the music performance. The major difficulty of the source separation problem is to resolve overlapping partials. Our solution collects the training data from isolated tones to train our Piano Model which can capture the common properties across the reappearance of pitches that helps to separate the mixtures. This approach enables high separation quality even for the case of octaves in which the partials of the upper tone completely overlap with those of the lower tone. The results show that our proposed system gives robust and accurate separation of piano tone signal mixtures (including octaves), with the quality significantly better than those reported in the previous work.