DCCRN-M

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 EnhancementonWSJ0 + DEMAND + RNNoise
PESQ-NB· 2021-02-03
3.28
best: 3.44 (DCUNet-MC)
Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses arXiv:2102.01993
Speech EnhancementonDNS Challenge
PESQ-NB· 2021-02-03
3.15
best: 4.08 (ZipEnhancer (M))
Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses arXiv:2102.01993