Instrument Separation of Symbolic Music by Explicitly Guided Diffusion Model

Similar to colorization in computer vision, instrument separation is to assign instrument labels (e.g. piano, guitar…) to notes from unlabeled mixtures which contain only performance information. To address the problem, we adopt diffusion models and explicitly guide them to preserve consistency between mixtures and music. The quantitative results show that our proposed model can generate high-fidelity samples for multitrack symbolic music with creativity.