From: Time-domain adaptive attention network for single-channel speech separation
i | Model | \(\overline{D}\) | \(S_D\) | \(\hat{S_D}\) | t | p | \(\alpha\) |
---|---|---|---|---|---|---|---|
1 | DPRNN-TAANet | 1.86 | 5.50 | 0.107 | 17.34 | \(7.58\times {10^{-64}}\) | 0.05 |
2 | DPTNet-TAANet | 0.61 | 2.95 | 0.058 | 10.52 | \(2.25\times {10^{-25}}\) | 0.05 |