Speaker Verification on VoxCeleb1 hard (H)
0.92EERfwSE-ResNet-200
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| fwSE-ResNet-200Post-training pipeline=Model Averaging, LM-FT, CMF, AS-Norm, and QMF2026.06 | 0.92 | 0.086 | — | |
| Xi-VectorPost-training pipeline=Model Averaging, LM-FT, CMF, AS-Norm, and QMF2026.06 | 0.98 | 0.09 | — | |
| ECAPA2Post-training pipeline=Model Averaging, LM-FT, CMF, AS-Norm, and QMF2026.06 | 1.01 | 0.091 | — | |
| ReDimNetPost-training pipeline=Model Averaging, LM-FT, CMF, AS-Norm, and QMF2026.06 | 1.14 | 0.11 | — | |
| NeXt-TDNN (C=256, B=3)Params=7.1M, MACs=2.027G, RTF (x10^-3)=1.31, Model Scale=base2023.12 | 1.82 | 0.1818 | — | |
| NeXt-TDNN-l(C=256, B=3)Params=6.0M, MACs=1.695G, RTF (x10^-3)=0.88, Model Scale=base2023.12 | 1.86 | 0.1844 | — | |
| NeXt-TDNN (C=384, B=1)Params=6.7M, MACs=1.862G, RTF (x10^-3)=0.71, Model Scale=base2023.12 | 1.89 | 0.1758 | — | |
| NeXt-TDNN (C=128, B=3)Params=1.9M, MACs=0.519G, RTF (x10^-3)=1.29, Model Scale=mobile2023.12 | 1.98 | 0.1903 | — | |
| NeXt-TDNN-l(C=384, B=1)Params=5.9M, MACs=1.609G, RTF (x10^-3)=0.63, Model Scale=base2023.12 | 2.02 | 0.1882 | — | |
| NeXt-TDNN-l(C=128, B=3)Params=1.6M, MACs=0.441G, RTF (x10^-3)=0.89, Model Scale=mobile2023.12 | 2.12 | 0.2006 | — | |
| EfficientTDNN-BaseParams=5.8M, MACs=1.450G, RTF (x10^-3)=1.32, Model Scale=base2023.12 | 2.17 | 0.2073 | — | |
| Fair-Gate2026.03 | 2.25 | 0.26 | 0.07 | |
| NeXt-TDNN (C=192, B=1)Params=1.8M, MACs=0.478G, RTF (x10^-3)=0.63, Model Scale=mobile2023.12 | 2.28 | 0.2073 | — | |
| VoxDisentangler2026.03 | 2.4 | 0.26 | 0.1 | |
| ECAPA-TDNN (C=512)Params=6.2M, MACs=1.569G, RTF (x10^-3)=1.80, Model Scale=base2023.12 | 2.44 | 0.2368 | — | |
| NeXt-TDNN-l(C=192, B=1)Params=1.6M, MACs=0.417G, RTF (x10^-3)=0.51, Model Scale=mobile2023.12 | 2.49 | 0.2274 | — | |
| ECAPA-TDNN + GRL2026.03 | 2.57 | 0.28 | 0.1 | |
| ECAPA-TDNN2026.03 | 2.62 | 0.25 | 0.1 | |
| ECAPA-TDNN (C=256)Params=1.9M, MACs=0.410G, RTF (x10^-3)=1.60, Model Scale=mobile2023.12 | 2.7 | 0.2512 | — | |
| EfficientTDNN-MobileParams=2.4M, MACs=0.574G, RTF (x10^-3)=1.20, Model Scale=mobile2023.12 | 2.72 | 0.2526 | — | |
| Fast ResNet-34Params=1.4M, MACs=0.675G, RTF (x10^-3)=1.67, Model Scale=mobile2023.12 | 4.19 | 0.3797 | — |