| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Speaker Verification | VoxCeleb1 with MUSAN noise (test) | EER1.91 | 187 | |
| Speaker Verification | VoxCeleb1 (Vox1-O) | EER0.14 | 160 | |
| Speaker Recognition | VoxCeleb1 (test) | EER2.21 | 126 | |
| Speaker Verification | VoxCeleb1 (Vox1-H) | EER0.55 | 103 | |
| Speaker Verification | VoxCeleb-E | EER0.27 | 95 | |
| Speaker Verification | VoxCeleb1 (test) | Cosine EER0.22 | 85 | |
| Speaker Identification | VoxCeleb1 | Accuracy97.5 | 58 | |
| Speaker Verification | VoxCeleb1 Hard Cleaned | EER0.0099 | 45 | |
| Speaker Verification | VoxCeleb1 Cleaned (Extended) | EER (%)0.48 | 45 | |
| Speaker Verification | Vox-H VoxCeleb2 (test) | EER2.239 | 38 | |
| Speaker Verification | VoxCeleb2 O (test) | EER1.005 | 38 | |
| Speaker Verification | VoxCeleb1 with Nonspeech100 (test) | EER (%)2.19 | 36 | |
| Speaker Identification | VoxCeleb 1 | Normalized Score98.5 | 28 | |
| Audio-visual target speaker extraction | VoxCeleb-2mix impaired visual scenarios (test) | SI-SNR11.27 | 27 | |
| Speaker Verification | VoxCeleb1 extended (test) | EER1.07 | 25 | |
| Speaker Verification | VoxCeleb1-50 | Balanced Accuracy95.7 | 24 | |
| Speaker verification | VoxCeleb 1 (verification) | EER0.48 | 22 | |
| Speaker Verification | VoxCeleb1 hard (H) | EER0.92 | 21 | |
| Speaker Verification | VoxCeleb1 extended | EER1.04 | 21 | |
| Speaker Extraction | VoxCeleb2 mix Clean Visual | SI-SNR (dB)11.61 | 17 | |
| Audio-visual speech separation | VoxCeleb2 (test) | SI-SNRi14.6 | 16 | |
| Face Reenactment | VoxCeleb2 (test) | FID24.92 | 16 | |
| Face Reenactment | VoxCeleb1 (test) | SSIM0.804 | 16 | |
| Speaker Verification | VoxCeleb1 Black-box FAKEBOB | ASR Error Rate2.4 | 15 | |
| Speaker Verification | VoxCeleb1 Targeted PGD-ℓ2 | EER (10 iter)2.6 | 15 |