aTENNuate

Reported on 6 benchmarks across 1 task · 1 paper · 1 SOTA

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

Audio6 results

Speech EnhancementonVoiceBank + DEMAND
SI-SDR· 2024-09-05
15.04
best: 19.96 (ZipEnhancer (S, \lamba_6 = 0.2))
SOTA
aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio arXiv:2409.03377
Speech EnhancementonDeep Noise Suppression (DNS) Challenge
PESQ-WB· 2024-09-05
2.98
best: 3.81 (ZipEnhancer (M))
aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio arXiv:2409.03377
Speech EnhancementonVoiceBank + DEMAND
CBAK· 2024-09-05
2.85
best: 3.99 (MP-SENet)
aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio arXiv:2409.03377
Speech EnhancementonVoiceBank + DEMAND
COVL· 2024-09-05
3.96
best: 4.4 (Mamba-SEUNet L (+PCS))
aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio arXiv:2409.03377
Speech EnhancementonVoiceBank + DEMAND
CSIG· 2024-09-05
4.57
best: 4.82 (Mamba-SEUNet L (+PCS))
aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio arXiv:2409.03377
Speech EnhancementonVoiceBank + DEMAND
PESQ (wb)· 2024-09-05
3.27
best: 3.99 (ROSE-CD(PESQ))
aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio arXiv:2409.03377