Neural Symbolic Music Genre Transfer Insights

Abstract

Transferring a song from one genre to another is most difficult if no instrumentation information is provided and genre is only defined by the timing and pitch of the played notes. Inspired by the CycleGAN music genre transfer presented in [2] we investigate whether recent additions to GAN training like spectral normalization and self-attention can improve transfer. Our preliminary results show that spectral normalization improves audible quality, while self-attention hurts content retention due to its non-locality. We further provide insights into genre attribution, showing that often only few notes are genre-decisive.