Table 4 SDRi/SI-SNRi performance of DPCCN with CPS-1 and SCT-1 on Aishell2Mix test set
From: Heterogeneous separation consistency training for adaptation of unsupervised speech separation
Top \(p\%\)SCM | Adaptation | SDRi (dB) | SI-SNRi (dB) |
|---|---|---|---|
\(p=10\%\) | - | 5.24 | 4.49 |
\(p=25\%\) | - | 5.65 | 5.05 |
\(p=50\%\) | - | 5.66 | 5.11 |
\(\checkmark\) | 5.98 | 5.32 |