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.
| Name | Size | |
|---|---|---|
|
204_Paper.pdf
md5:01b676ea21c800affea5264e56c5650d |
418.8 kB | Download |
| All versions | This version | |
|---|---|---|
| Views | 96 | 98 |
| Downloads | 60 | 60 |
| Data volume | 25.1 MB | 25.1 MB |
| Unique views | 93 | 95 |
| Unique downloads | 54 | 54 |
- Publication date:
- September 23, 2018
- DOI:
-
- Published in:
- Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR, Paris, France, pp. 747-754.
- Meeting:
- International Society for Music Information Retrieval Conference (ISMIR 2018), Paris, France, September 23-27, 2018
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International