EVA-GAN: Enhanced Various Audio Generation Via Scalable Generative Adversarial Networks

Abstract

The advent of Large Models marks a new era in machine learning, significantly outperforming smaller models by leveraging vast datasets to capture and synthesize complex patterns. Despite these advancements, the exploration into scaling, especially in the audio generation domain, remains limited, with previous efforts didn't extend into the high-fidelity (HiFi) 44.1kHz domain and suffering from both spectral discontinuities and blurriness in the high-frequency domain, alongside a lack of robustness against out-of-domain data. These limitations restrict the applicability of models to diverse use cases, including music and singing generation. Our work introduces Enhanced Various Audio Generation via Scalable Generative Adversarial Networks (EVA-GAN), yields significant improvements over previous state-of-the-art in spectral and high-frequency reconstruction and robustness in out-of-domain data performance, enabling the generation of HiFi audios by employing an extensive dataset of 36,000

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliao2024eva

Related papers

• Bigvgan: A Universal Neural Vocoder With Large-scale Training (2022)6.17
• Hifi-gan: Generative Adversarial Networks For Efficient And High Fidelity Speech Synthesis (2020)0.00
• Bandwidth Extension On Raw Audio Via Generative Adversarial Networks (2019)0.00
• RAVE: A Variational Autoencoder For Fast And High-quality Neural Audio Synthesis (2021)0.00
• Specdiff-gan: A Spectrally-shaped Noise Diffusion GAN For Speech And Music Synthesis (2024)7.81
• Hifi-wavegan: Generative Adversarial Network With Auxiliary Spectrogram-phase Loss For High-fidelity Singing Voice Generation (2022)0.00
• Hifi++: A Unified Framework For Bandwidth Extension And Speech Enhancement (2022)11.93
• Gansynth: Adversarial Neural Audio Synthesis (2019)0.00