PERL-AE

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· uses extra data· 2020-10-22
3.53
best: 3.99 (MP-SENet)
SOTA
Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised Models arXiv:2010.11860
Speech EnhancementonVoiceBank + DEMAND
COVL· uses extra data· 2020-10-22
3.83
best: 4.4 (Mamba-SEUNet L (+PCS))
SOTA
Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised Models arXiv:2010.11860
Speech EnhancementonVoiceBank + DEMAND
CSIG· uses extra data· 2020-10-22
4.43
best: 4.82 (Mamba-SEUNet L (+PCS))
SOTA
Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised Models arXiv:2010.11860
Speech EnhancementonVoiceBank + DEMAND
PESQ (wb)· uses extra data· 2020-10-22
3.17
best: 3.99 (ROSE-CD(PESQ))
SOTA
Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised Models arXiv:2010.11860