Speaker Extraction on YGD 2mix
10.7SI-SNRi (dB)SeLG
Evaluation results
| Method | Links | |
|---|---|---|
| SeLGModalities=Lip & Gesture, Fusion=Attention, Loss=L_SI-SNR + L_emb2026.01 | 10.7 | |
| SeLG†Modalities=Lip & Gesture, Fusion=Attention, Loss=L_SI-SNR2026.01 | 10.1 | |
| SeLG◦Modalities=Lip & Gesture, Fusion=Concatenation, Loss=L_SI-SNR2026.01 | 9.5 | |
| SEGModalities=Gesture, Fusion=Concatenation, Loss=L_SI-SNR + L_emb2026.01 | -0.1 | |
| SEGModalities=Gesture, Fusion=Concatenation, Loss=L_SI-SNR2026.01 | -1.4 | |
| USEVModalities=Lip, Fusion=Concatenation, Loss=L_SI-SNR2026.01 | -2.2 |