Bigwavgan: A Wave-to-wave Generative Adversarial Network For Music Super-resolution

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 signifi

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2023bigwavgan

Related papers

• An Investigation Of Pre-upsampling Generative Modelling And Generative Adversarial Networks In Audio Super Resolution (2021)0.00
• Phase-aware Music Super-resolution Using Generative Adversarial Networks (2020)9.59
• Bandwidth Extension On Raw Audio Via Generative Adversarial Networks (2019)0.00
• A Unified Neural Architecture For Instrumental Audio Tasks (2019)0.00
• Gansynth: Adversarial Neural Audio Synthesis (2019)0.00
• Melgan: Generative Adversarial Networks For Conditional Waveform Synthesis (2019)0.00
• Adversarial Audio Synthesis (2018)0.00
• EVA-GAN: Enhanced Various Audio Generation Via Scalable Generative Adversarial Networks (2024)0.00