Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin
This addresses the problem of making AI music tools accessible for musicians and producers in their daily work, though it is incremental as it applies existing methods to a new application.
The paper tackles the difficulty for musicians to use deep learning music generation in practice by proposing a VAE-based rhythm generator that trains on selected MIDI files and generates rhythms, implemented as a DAW plugin for Ableton Live, with professional users finding it creatively useful.
There has been significant progress in the music generation technique utilizing deep learning. However, it is still hard for musicians and artists to use these techniques in their daily music-making practice. This paper proposes a Variational Autoencoder\cite{Kingma2014}(VAE)-based rhythm generation system, in which musicians can train a deep learning model only by selecting target MIDI files, then generate various rhythms with the model. The author has implemented the system as a plugin software for a DAW (Digital Audio Workstation), namely a Max for Live device for Ableton Live. Selected professional/semi-professional musicians and music producers have used the plugin, and they proved that the plugin is a useful tool for making music creatively. The plugin, source code, and demo videos are available online.