MANNER

Reported on 5 benchmarks across 1 task · 1 paper · 3 SOTA

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

Audio5 results

Speech EnhancementonVoiceBank + DEMAND
CBAK· 2022-03-04
3.65
best: 3.99 (MP-SENet)
SOTA
MANNER: Multi-view Attention Network for Noise Erasure arXiv:2203.02181
Speech EnhancementonVoiceBank + DEMAND
COVL· 2022-03-04
3.91
best: 4.4 (Mamba-SEUNet L (+PCS))
SOTA
MANNER: Multi-view Attention Network for Noise Erasure arXiv:2203.02181
Speech EnhancementonVoiceBank + DEMAND
CSIG· 2022-03-04
4.53
best: 4.82 (Mamba-SEUNet L (+PCS))
SOTA
MANNER: Multi-view Attention Network for Noise Erasure arXiv:2203.02181
Speech EnhancementonVoiceBank + DEMAND
PESQ (wb)· 2022-03-04
3.21
best: 3.99 (ROSE-CD(PESQ))
MANNER: Multi-view Attention Network for Noise Erasure arXiv:2203.02181
Speech EnhancementonVoiceBank + DEMAND
STOI· 2022-03-04
95
best: 96.22 (ZipEnhancer (S, \lamba_6 = 0.2))
MANNER: Multi-view Attention Network for Noise Erasure arXiv:2203.02181