Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/EVA-GAN-big

EVA-GAN-big

Reported on 12 benchmarks across 3 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio12 results

Speech RecognitiononLibriTTS
M-STFT· uses extra data· 2024-01-31
0.7982
best: 2.2358 (SC-WaveRNN)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Speech RecognitiononLibriTTS
PESQ· uses extra data· 2024-01-31
4.3536
best: 4.454 (PeriodWave-Turbo-L)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Speech RecognitiononLibriTTS
Periodicity· uses extra data· 2024-01-31
0.0751
best: 0.3044 (SC-WaveRNN)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Speech RecognitiononLibriTTS
V/UV F1· uses extra data· 2024-01-31
0.9745
best: 0.9793 (BigVGAN-v2)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Speech SynthesisonLibriTTS
M-STFT· uses extra data· 2024-01-31
0.7982
best: 2.2358 (SC-WaveRNN)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Speech SynthesisonLibriTTS
PESQ· uses extra data· 2024-01-31
4.3536
best: 4.454 (PeriodWave-Turbo-L)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Speech SynthesisonLibriTTS
Periodicity· uses extra data· 2024-01-31
0.0751
best: 0.3044 (SC-WaveRNN)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Speech SynthesisonLibriTTS
V/UV F1· uses extra data· 2024-01-31
0.9745
best: 0.9793 (BigVGAN-v2)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Accented Speech RecognitiononLibriTTS
M-STFT· uses extra data· 2024-01-31
0.7982
best: 2.2358 (SC-WaveRNN)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Accented Speech RecognitiononLibriTTS
PESQ· uses extra data· 2024-01-31
4.3536
best: 4.454 (PeriodWave-Turbo-L)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Accented Speech RecognitiononLibriTTS
Periodicity· uses extra data· 2024-01-31
0.0751
best: 0.3044 (SC-WaveRNN)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892
Accented Speech RecognitiononLibriTTS
V/UV F1· uses extra data· 2024-01-31
0.9745
best: 0.9793 (BigVGAN-v2)
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks arXiv:2402.00892