Target Speaker Extraction on REAL-T AMI English
2.178DNSMOS OVRLMeanFlowTSE
Evaluation Results
| Method | Links | |
|---|---|---|
| MeanFlowTSEMR predictor=without, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 2.178 | |
| AlphaFlowTSEMR predictor=with, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 2.169 | |
| MeanFlowTSEMR predictor=with, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 2.12 | |
| AD-FlowTSEMR predictor=without, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 1.837 | |
| AlphaFlowTSEMR predictor=without, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 1.82 | |
| AD-FlowTSEMR predictor=with, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 1.799 |