DeepFilterNet3

Reported on 5 benchmarks across 1 task · 1 paper

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· 2023-05-14
3.61
best: 3.99 (MP-SENet)
DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement arXiv:2305.08227
Speech EnhancementonVoiceBank + DEMAND
COVL· 2023-05-14
3.77
best: 4.4 (Mamba-SEUNet L (+PCS))
DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement arXiv:2305.08227
Speech EnhancementonVoiceBank + DEMAND
CSIG· 2023-05-14
4.34
best: 4.82 (Mamba-SEUNet L (+PCS))
DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement arXiv:2305.08227
Speech EnhancementonVoiceBank + DEMAND
PESQ (wb)· 2023-05-14
3.17
best: 3.99 (ROSE-CD(PESQ))
DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement arXiv:2305.08227
Speech EnhancementonVoiceBank + DEMAND
STOI· 2023-05-14
0.944
best: 96.22 (ZipEnhancer (S, \lamba_6 = 0.2))
DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement arXiv:2305.08227