MetricGAN

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Audio4 results

Speech EnhancementonVoiceBank + DEMAND
CBAK· 2019-05-13
3.18
best: 3.99 (MP-SENet)
SOTA
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement arXiv:1905.04874
Speech EnhancementonVoiceBank + DEMAND
COVL· 2019-05-13
3.42
best: 4.4 (Mamba-SEUNet L (+PCS))
SOTA
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement arXiv:1905.04874
Speech EnhancementonVoiceBank + DEMAND
CSIG· 2019-05-13
3.99
best: 4.82 (Mamba-SEUNet L (+PCS))
SOTA
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement arXiv:1905.04874
Speech EnhancementonVoiceBank + DEMAND
PESQ (wb)· 2019-05-13
2.86
best: 3.99 (ROSE-CD(PESQ))
SOTA
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement arXiv:1905.04874