Speaker Extraction on YGD-3mix (test)
11.7SI-SNRi (dB)SeLG
Evaluation Results
| Method | Links | |
|---|---|---|
| SeLGModalities=Lip & Gesture, Fusion=Attention, Loss=L_SI-SNR + L_emb2026.01 | 11.7 | |
| SeLG†Modalities=Lip & Gesture, Fusion=Attention, Loss=L_SI-SNR2026.01 | 11.3 | |
| SeLG◦Modalities=Lip & Gesture, Fusion=Concatenation, Loss=L_SI-SNR2026.01 | 11.1 | |
| USEVModalities=Lip, Fusion=Concatenation, Loss=L_SI-SNR2026.01 | 9.5 | |
| SEGModalities=Gesture, Fusion=Concatenation, Loss=L_SI-SNR + L_emb2026.01 | 4.7 | |
| SEGModalities=Gesture, Fusion=Concatenation, Loss=L_SI-SNR2026.01 | 4 |