GANs & Reels: Creating Irish Music using a Generative Adversarial Network
Sound
2020-10-30 v1 Machine Learning
Audio and Speech Processing
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 DC-GAN 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.
Cite
@article{arxiv.2010.15772,
title = {GANs & Reels: Creating Irish Music using a Generative Adversarial Network},
author = {Antonina Kolokolova and Mitchell Billard and Robert Bishop and Moustafa Elsisy and Zachary Northcott and Laura Graves and Vineel Nagisetty and Heather Patey},
journal= {arXiv preprint arXiv:2010.15772},
year = {2020}
}
Comments
7 pages, (+ 2 pages of references)