Learning to Fuse Music Genres with Generative Adversarial Dual Learning

TL;DR

FusionGAN introduces a novel music genre fusion framework that combines generative adversarial networks and dual learning, utilizing Wasserstein distance for effective genre merging and style integration.

Contribution

The paper presents a new dual learning extension for GANs that effectively fuses music genres using Wasserstein metrics, addressing domain difference quantification and gradient issues.

Findings

Successfully merges two music genres in experiments

Uses Wasserstein distance to measure domain differences

Effective style integration demonstrated on public datasets

Abstract

FusionGAN is a novel genre fusion framework for music generation that integrates the strengths of generative adversarial networks and dual learning. In particular, the proposed method offers a dual learning extension that can effectively integrate the styles of the given domains. To efficiently quantify the difference among diverse domains and avoid the vanishing gradient issue, FusionGAN provides a Wasserstein based metric to approximate the distance between the target domain and the existing domains. Adopting the Wasserstein distance, a new domain is created by combining the patterns of the existing domains using adversarial learning. Experimental results on public music datasets demonstrated that our approach could effectively merge two genres.