U-Net (Real)

Reported on 2 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.

Audio2 results

Speech EnhancementonCHiME-3
PESQ· 2020-01-30
2.176
best: 2.67 (Inter-Channel Conv-TasNet)
Channel-Attention Dense U-Net for Multichannel Speech Enhancement arXiv:2001.11542
Speech EnhancementonCHiME-3
SDR· 2020-01-30
15.967
best: 19.67 (Inter-Channel Conv-TasNet)
Channel-Attention Dense U-Net for Multichannel Speech Enhancement arXiv:2001.11542