| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| VoxCeleb1 (test) | Angular Prototypical | EER2.21 | 126 | 4mo ago | |
| VoxCeleb1 original (vox1-o) | SpeakerRPL V2 | EER (mean)0.24 | 13 | 3mo ago | |
| VoxCeleb (test) | ESC | EER0.94 | 11 | 4mo ago | |
| VoxCeleb1 extended (vox1-e) | EER (mean)0.9 | 11 | 4mo ago | ||
| SITW (Speakers In The Wild) core-core protocol | ReDimNet-B6 | EER0.77 | 9 | 4mo ago | |
| DramaSR 532K 428K utterances (test) | DramaSR-LRM | Accuracy (All)87.79 | 8 | 22d ago | |
| VoxCeleb | GradCAM | Modified RISE-eval8.9 | 8 | 1mo ago | |
| VoxCeleb Hard 1 | Proposed RecXi | EER0.0186 | 6 | 4mo ago | |
| Speaker Recognition Dataset | DUAP | ECAPA-TDNN Score1 | 5 | 4mo ago | |
| VoxCeleb B protocol 1 | ReDimNet-B6 | EER1.66 | 5 | 4mo ago | |
| VOICES from a Distance Challenge (Evaluation Set) | ReDimNet-B6 | EER3.19 | 5 | 4mo ago | |
| AudioMnist (test) | Parallel feature-free Audio processing | Accuracy70.51 | 2 | 1mo ago | |
| AudioMnist (train) | Parallel feature-free Audio processing | Accuracy71.79 | 2 | 1mo ago | |
| Ti-46 (test) | Parallel feature-free Audio processing | Accuracy53.14 | 2 | 1mo ago | |
| Ti-46 (train) | Parallel feature-free Audio processing | Accuracy66.67 | 2 | 1mo ago |
