GANs & Reels: Creating Irish Music using a Generative Adversarial Network
Antonina Kolokolova, Mitchell Billard, Robert H. Bishop, Moustafa Elsisy, Zachary Northcott, Laura M. Graves, Vineel Nagisetty, Heather Patey · arXiv (Cornell University) · 2020
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.