ML Anthology

Non-Sequential Melody Generation

Mitchell Billard, Robert Bishop, Moustafa Elsisy, Laura Graves, Antonina Kolokolova, Vineel Nagisetty, Zachary Northcott, Heather Patey
ICLR 2020
/iclr/2020/billard2020iclr-nonsequential/

Abstract

In this paper we present a method for algorithmic melody generation using a generative adversarial network without recurrent components. Music generation has been successfully done using recurrent neural networks, where the model learns sequence information that can help create authentic sounding melodies. Here, we use DCGAN architecture with dilated convolutions and towers to capture sequential information as spatial image information, and learn long-range dependencies in fixed-length melody forms such as Irish traditional reel.

PDF ICLR Semantic Scholar

Cite

Text

Billard et al. "Non-Sequential Melody Generation." International Conference on Learning Representations, 2020.

Markdown

[Billard et al. "Non-Sequential Melody Generation." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/billard2020iclr-nonsequential/)

BibTeX

@inproceedings{billard2020iclr-nonsequential,
  title     = {{Non-Sequential Melody Generation}},
  author    = {Billard, Mitchell and Bishop, Robert and Elsisy, Moustafa and Graves, Laura and Kolokolova, Antonina and Nagisetty, Vineel and Northcott, Zachary and Patey, Heather},
  booktitle = {International Conference on Learning Representations},
  year      = {2020},
  url       = {https://mlanthology.org/iclr/2020/billard2020iclr-nonsequential/}
}