Can GAN originate new electronic dance music genres? -- Generating novel rhythm patterns using GAN with Genre Ambiguity Loss

TL;DR

This paper explores using an extended GAN framework with Genre Ambiguity Loss to generate novel electronic dance music rhythms that diverge from existing genre patterns, demonstrating potential for creative music generation.

Contribution

Introduces a GAN-based method with Genre Ambiguity Loss to produce new rhythm patterns outside the training data's genre distributions.

Findings

Generated rhythms sound like music but are genre-ambiguous.

The method successfully diverges from dataset's inherent distributions.

Source code and tools are publicly available.

Abstract

Since the introduction of deep learning, researchers have proposed content generation systems using deep learning and proved that they are competent to generate convincing content and artistic output, including music. However, one can argue that these deep learning-based systems imitate and reproduce the patterns inherent within what humans have created, instead of generating something new and creative. This paper focuses on music generation, especially rhythm patterns of electronic dance music, and discusses if we can use deep learning to generate novel rhythms, interesting patterns not found in the training dataset. We extend the framework of Generative Adversarial Networks(GAN) and encourage it to diverge from the dataset's inherent distributions by adding additional classifiers to the framework. The paper shows that our proposed GAN can generate rhythm patterns that sound like music rhythms but do not belong to any genres in the training dataset. The source code, generated rhythm patterns, and a supplementary plugin software for a popular Digital Audio Workstation software are available on our website.