Target Speaker Extraction on REAL-T DipCo English
1.56DNSMOS OVRLAlphaFlowTSE
Evaluation Results
| Method | Links | |
|---|---|---|
| AlphaFlowTSEMR predictor=without, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 1.56 | |
| AlphaFlowTSEMR predictor=with, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 1.515 | |
| MeanFlowTSEMR predictor=with, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 1.475 | |
| AD-FlowTSEMR predictor=without, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 1.346 | |
| AD-FlowTSEMR predictor=with, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 1.252 | |
| MeanFlowTSEMR predictor=without, Training set=Libri2Mix noisy, Zero-shot=true2026.03 | 1.193 |