Papers › EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks
Shijia Liao, Shiyi Lan, Arun George Zachariah
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 hours of 44.1kHz audio, a context-aware module, a Human-In-The-Loop artifact measurement toolkit, and expands the model to approximately 200 million parameters. Demonstrations of our work are available at https://double-blind-eva-gan.cc.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Speech Synthesis | LibriTTS | EVA-GAN-big | M-STFT | 0.7982 | #3 of 15 | Archive leaderboard | report |
| Speech Synthesis | LibriTTS | EVA-GAN-big | PESQ | 4.3536 | #3 of 15 | Archive leaderboard | report |
| Speech Synthesis | LibriTTS | EVA-GAN-big | Periodicity | 0.0751 | #3 of 15 | Archive leaderboard | report |
| Speech Synthesis | LibriTTS | EVA-GAN-big | V/UV F1 | 0.9745 | #3 of 15 | Archive leaderboard | report |
| Speech Synthesis | LibriTTS | EVA-GAN-base | M-STFT | 0.9485 | #8 of 15 | Archive leaderboard | report |
| Speech Synthesis | LibriTTS | EVA-GAN-base | PESQ | 4.0330 | #8 of 15 | Archive leaderboard | report |
| Speech Synthesis | LibriTTS | EVA-GAN-base | Periodicity | 0.0942 | #8 of 15 | Archive leaderboard | report |
| Speech Synthesis | LibriTTS | EVA-GAN-base | V/UV F1 | 0.9658 | #8 of 15 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections