Target Speaker Extraction on Vietnamese zero-shot
14.6SI-SDRWHYV
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| WHYVTraining Dataset=Libri2Mix2024.10 | 14.6 | 14.9 | 3.2 | |
| SpeakerBeamTraining Dataset=Libri2Mix2024.10 | 11.1 | 11.3 | 2.4 | |
| WHYVTraining Dataset=WHAMR!2024.10 | 7.7 | 6.7 | 2.3 | |
| X-TF-GridnetTraining Dataset=WHAMR!2024.10 | 5.8 | 5.1 | 2 | |
| BSRNNTraining Dataset=VoxCeleb12024.10 | 4.6 | 1.9 | 1.7 |