Speech Separation on WHAM! 2-speaker (test)
18.4SI-SNRiSepReformer (L) + DM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SepReformer (L) + DM# Params (M)=55.3, GMAC/s (G/s)=155.5, Model scale=L, dynamic mixing (+DM)=true2025.07 | 18.4 | 18.7 | |
| MossFormer2 + DM# Params (M)=55.7, GMAC/s (G/s)=84.2, dynamic mixing (+DM)=true2025.07 | 18.1 | — | |
| SepReformer (M)# Params (M)=17.3, GMAC/s (G/s)=81.3, Model scale=M2025.07 | 17.8 | 18.1 | |
| PRESS-12 @ 12 (M) + FT# Params (M)=22.4, GMAC/s (G/s)=79.7, Model scale=M, Exit point=12, finetuned (+FT)=true2025.07 | 17.49 | 17.89 | |
| MossFormer (L) + DM# Params (M)=42.1, GMAC/s (G/s)=70.4, Model scale=L, dynamic mixing (+DM)=true2025.07 | 17.3 | — | |
| SepReformer (S)# Params (M)=4.5, GMAC/s (G/s)=21.3, Model scale=S2025.07 | 17.3 | 17.7 | |
| PRESS-4 @ 4 (S) + FT# Params (M)=3.4, GMAC/s (G/s)=11.3, Model scale=S, Exit point=4, finetuned (+FT)=true2025.07 | 17.25 | 17.58 | |
| PRESS-12 @ 8 (M) + FT# Params (M)=15.6, GMAC/s (G/s)=54.4, Model scale=M, Exit point=8, finetuned (+FT)=true2025.07 | 17.21 | 17.34 | |
| SepReformer (T)# Params (M)=3.7, GMAC/s (G/s)=10.4, Model scale=T2025.07 | 17.2 | 17.5 | |
| PRESS-12 @ 12 (M)# Params (M)=22.4, GMAC/s (G/s)=79.7, Model scale=M, Exit point=122025.07 | 16.65 | 17.12 | |
| PRESS-12 @ 8 (M)# Params (M)=15.6, GMAC/s (G/s)=54.4, Model scale=M, Exit point=82025.07 | 16.57 | 17.03 | |
| PRESS-4 @ 4 (S)# Params (M)=3.4, GMAC/s (G/s)=11.3, Model scale=S, Exit point=42025.07 | 16.49 | 16.91 | |
| PRESS-12 @ 4 (M) + FT# Params (M)=8.7, GMAC/s (G/s)=29.1, Model scale=M, Exit point=4, finetuned (+FT)=true2025.07 | 16.47 | 16.81 | |
| PRESS-12 @ 4 (M)# Params (M)=8.7, GMAC/s (G/s)=29.1, Model scale=M, Exit point=42025.07 | 16.43 | 16.71 | |
| SepFormer + DM# Params (M)=26.0, GMAC/s (G/s)=86.9, dynamic mixing (+DM)=true2025.07 | 16.4 | 16.7 | |
| SepFormer# Params (M)=26.0, GMAC/s (G/s)=86.92025.07 | 14.7 | 16.8 | |
| DualPathRNN# Params (M)=2.6, GMAC/s (G/s)=42.52025.07 | 13.7 | 14.1 | |
| Conv-TasNet# Params (M)=5.1, GMAC/s (G/s)=10.52025.07 | 12.7 | — |