From: Heterogeneous separation consistency training for adaptation of unsupervised speech separation
SCT | System | #Iter | CPS-1 | CPS-2 | Oracle |
---|---|---|---|---|---|
SCT-1 | Conv-TasNet | 1 | 5.14/4.63 | 5.47/4.90 | 5.98/5.39 |
2 | 5.45/4.94 | 5.99/5.39 | 6.18/5.57 | ||
DPCCN | 1 | 5.98/5.32 | 5.90/5.25 | 6.00/5.31 | |
2 | 6.17/5.50 | 6.03/5.39 | 6.10/5.44 | ||
SCT-2 | Conv-TasNet | 1 | 5.14/4.63 | 5.47/4.90 | 5.98/5.39 |
2 | 5.36/4.89 | 6.15/5.52 | 6.21/5.65 | ||
DPCCN | 1 | 6.05/5.52 | 6.48/5.82 | 6.79/6.19 | |
2 | 5.49/5.05 | 6.43/5.81 | 6.45/5.91 | ||
SCT-3 | Conv-TasNet | 1 | 5.14/4.63 | 5.47/4.90 | - |
2 | 5.43/4.93 | 5.77/5.24 | - | ||
DPCCN | 1 | 6.14/5.58 | 6.22/5.65 | - | |
2 | 6.02/5.52 | 6.10/5.56 | - |