BigWavGAN: A Wave-To-Wave Generative Adversarial Network for Music Super-Resolution

TL;DR

BigWavGAN is a novel wave-to-wave GAN model that significantly improves music super-resolution quality by integrating large-scale models with advanced discriminators and adversarial training, outperforming existing methods.

Contribution

The paper introduces BigWavGAN, combining Demucs with multi-scale and multi-resolution discriminators, enhancing music super-resolution beyond current state-of-the-art models.

Findings

Outperforms SOTA in simulated scenarios

Generates high perceptual quality music

Shows superior generalization to out-of-distribution data

Abstract

Generally, Deep Neural Networks (DNNs) are expected to have high performance when their model size is large. However, large models failed to produce high-quality results commensurate with their scale in music Super-Resolution (SR). We attribute this to that DNNs cannot learn information commensurate with their size from standard mean square error losses. To unleash the potential of large DNN models in music SR, we propose BigWavGAN, which incorporates Demucs, a large-scale wave-to-wave model, with State-Of-The-Art (SOTA) discriminators and adversarial training strategies. Our discriminator consists of Multi-Scale Discriminator (MSD) and Multi-Resolution Discriminator (MRD). During inference, since only the generator is utilized, there are no additional parameters or computational resources required compared to the baseline model Demucs. Objective evaluation affirms the effectiveness of BigWavGAN in music SR. Subjective evaluations indicate that BigWavGAN can generate music with significantly high perceptual quality over the baseline model. Notably, BigWavGAN surpasses the SOTA music SR model in both simulated and real-world scenarios. Moreover, BigWavGAN represents its superior generalization ability to address out-of-distribution data. The conducted ablation study reveals the importance of our discriminators and training strategies. Samples are available on the demo page.