BSRNN-S + MRSD

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Audio4 results

Speech EnhancementonDeep Noise Suppression (DNS) Challenge
PESQ-NB· 2022-12-01
3.89
best: 4.08 (ZipEnhancer (M))
SOTA
High Fidelity Speech Enhancement with Band-split RNN arXiv:2212.00406
Speech EnhancementonDeep Noise Suppression (DNS) Challenge
PESQ-WB· 2022-12-01
3.53
best: 3.81 (ZipEnhancer (M))
SOTA
High Fidelity Speech Enhancement with Band-split RNN arXiv:2212.00406
Speech EnhancementonDeep Noise Suppression (DNS) Challenge
SI-SDR-WB· 2022-12-01
21.4
best: 23.3 (TF-Locoformer (M))
SOTA
High Fidelity Speech Enhancement with Band-split RNN arXiv:2212.00406
Speech EnhancementonDeep Noise Suppression (DNS) Challenge
STOI· 2022-12-01
98.4
best: 98.8 (TF-Locoformer (M))
SOTA
High Fidelity Speech Enhancement with Band-split RNN arXiv:2212.00406