MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer
This work addresses style transfer in symbolic music for applications in music generation and editing, representing a novel but domain-specific advancement.
The paper tackles the problem of modeling polyphonic music with multiple instruments and dynamics for style transfer, achieving the first successful neural style transfer on complete musical compositions by automatically changing pitches, dynamics, and instruments between styles like Classical and Jazz.
We introduce MIDI-VAE, a neural network model based on Variational Autoencoders that is capable of handling polyphonic music with multiple instrument tracks, as well as modeling the dynamics of music by incorporating note durations and velocities. We show that MIDI-VAE can perform style transfer on symbolic music by automatically changing pitches, dynamics and instruments of a music piece from, e.g., a Classical to a Jazz style. We evaluate the efficacy of the style transfer by training separate style validation classifiers. Our model can also interpolate between short pieces of music, produce medleys and create mixtures of entire songs. The interpolations smoothly change pitches, dynamics and instrumentation to create a harmonic bridge between two music pieces. To the best of our knowledge, this work represents the first successful attempt at applying neural style transfer to complete musical compositions.