Sudo rm-rf (U=8)

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

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

Audio2 results

Speech EnhancementonDeep Noise Suppression (DNS) Challenge
SI-SDR-WB· 2021-10-19
18.6
best: 23.3 (TF-Locoformer (M))
SOTA
Continual self-training with bootstrapped remixing for speech enhancement arXiv:2110.10103
Speech EnhancementonDeep Noise Suppression (DNS) Challenge
PESQ-WB· 2021-10-19
2.69
best: 3.81 (ZipEnhancer (M))
Continual self-training with bootstrapped remixing for speech enhancement arXiv:2110.10103