WHYV

Reported on 3 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.

Speech3 results

Speech SeparationonLibri2Mix
SDR· 2024-10-01
17.2458
SOTA
Wanna hear your voice? A sample is all we need!arXiv:2410.00527
Speech SeparationonLibri2Mix
SI-SDRi· 2024-10-01
17.5
best: 22.2 (MossFormer2 (w speed perturb))
Wanna hear your voice? A sample is all we need!arXiv:2410.00527
Speech SeparationonWHAM!
SI-SDRi· 2024-10-01
12.964
best: 18.4 (SepReformer-L + DM)
Wanna hear your voice? A sample is all we need!arXiv:2410.00527