Target Speaker Extraction on REAL-T AISHELL-4 Chinese
2.277DNSMOS OVRLAlphaFlowTSE
Evaluation Results
| Method | Links | |
|---|---|---|
| AlphaFlowTSEMR predictor=with, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 2.277 | |
| MeanFlowTSEMR predictor=with, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 2.258 | |
| AD-FlowTSEMR predictor=with, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 2.137 | |
| AD-FlowTSEMR predictor=without, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 2.113 | |
| AlphaFlowTSEMR predictor=without, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 2.002 | |
| MeanFlowTSEMR predictor=without, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 1.732 |