Conference paper Open Access

MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer

Gino Brunner; Andres Konrad; Yuyi Wang; Roger Wattenhofer

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.

Files (418.8 kB)
Name Size
204_Paper.pdf
md5:01b676ea21c800affea5264e56c5650d
418.8 kB Download
35
19
views
downloads
All versions This version
Views 3537
Downloads 1919
Data volume 8.0 MB8.0 MB
Unique views 3335
Unique downloads 1818

Share

Cite as