D2Former

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Audio2 results

Speech EnhancementonVoiceBank + DEMAND
PESQ (wb)· 2021-02-03
3.43
best: 3.99 (ROSE-CD(PESQ))
SOTA
Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses arXiv:2102.01993
Speech EnhancementonVoiceBank + DEMAND
Para. (M)· 2021-02-03
0.86
best: 65 (ROSE-CD(PESQ))
SOTA
Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses arXiv:2102.01993