SepMamba + DM (M)

Reported on 2 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.

Speech2 results

Speech SeparationonWSJ0-2mix
SDRi· 2024-10-28
22.9
best: 25.2 (TF-Locoformer (L) + DM)
SepMamba: State-space models for speaker separation using Mamba arXiv:2410.20997
Speech SeparationonWSJ0-2mix
SI-SDRi· 2024-10-28
22.7
best: 25.1 (TF-Locoformer (L) + DM)
SepMamba: State-space models for speaker separation using Mamba arXiv:2410.20997