Constrained Parameter Estimation of Harmonic and Inharmonic Models for Separating Polyphonic Musical Audio Signals

This paper describes a sound source separation method for polyphonic sound mixtures of music including both harmonic and inharmonic sounds, and constrained parameter estimation using standard MIDI files as prior information. The difficulties in dealing with both types of sound together have not been addressed in most previous methods that have focused on either of the two types separately, because the properties of these sounds are quite different. We therefore developed an integrated weighted-mixture model consisting of both harmonic-structure and inharmonic tone models. On the basis of the MAP estimation using the EM algorithm, we estimated all model parameters of this integrated model under several original constraints for preventing over-training and maintaining intra-instrument consistency. We confirmed that the integrated model increased the SNR by 1.5 dB.