Corpus ID: 214795187

Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin

@article{Tokui2020TowardsDM,
  title={Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin},
  author={N. Tokui},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.01525}
}
  • N. Tokui
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
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… Expand
1 Citations

References

SHOWING 1-10 OF 17 REFERENCES
Conditioning Deep Generative Raw Audio Models for Structured Automatic Music
  • 26
  • PDF
Learning to Groove with Inverse Sequence Transformations
  • 17
  • Highly Influential
  • PDF
This time with feeling: learning expressive musical performance
  • 60
  • PDF
A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
  • 180
  • Highly Influential
  • PDF
Text-based LSTM networks for Automatic Music Composition
  • 50
  • PDF
A Fast Learning Algorithm for Deep Belief Nets
  • 11,883
  • PDF
A Comparison of Rhythmic Dissimilarity Measures
  • 5
  • PDF
...
1
2
...