MFNET

Reported on 3 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.

Audio3 results

Speech EnhancementonDeep Noise Suppression (DNS) Challenge
PESQ-NB· 2023-06-07
3.74
best: 4.08 (ZipEnhancer (M))
A Mask Free Neural Network for Monaural Speech Enhancement arXiv:2306.04286
Speech EnhancementonDeep Noise Suppression (DNS) Challenge
PESQ-WB· 2023-06-07
3.43
best: 3.81 (ZipEnhancer (M))
A Mask Free Neural Network for Monaural Speech Enhancement arXiv:2306.04286
Speech EnhancementonDeep Noise Suppression (DNS) Challenge
SI-SDR-WB· 2023-06-07
20.31
best: 23.3 (TF-Locoformer (M))
A Mask Free Neural Network for Monaural Speech Enhancement arXiv:2306.04286