Speaker Verification on VoxCeleb1 extended
1.04EERNeXt-TDNN-l(C=256, B=3)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| NeXt-TDNN-l(C=256, B=3)Params=6.0M, MACs=1.695G, RTF (x10^-3)=0.88, Model Scale=base2023.12 | 1.04 | 0.1157 | — | |
| NeXt-TDNN (C=256, B=3)Params=7.1M, MACs=2.027G, RTF (x10^-3)=1.31, Model Scale=base2023.12 | 1.04 | 0.1152 | — | |
| Fair-Gate2026.03 | 1.11 | 0.14 | 0.05 | |
| NeXt-TDNN (C=384, B=1)Params=6.7M, MACs=1.862G, RTF (x10^-3)=0.71, Model Scale=base2023.12 | 1.11 | 0.116 | — | |
| VoxDisentangler2026.03 | 1.15 | 0.14 | 0.11 | |
| NeXt-TDNN (C=128, B=3)Params=1.9M, MACs=0.519G, RTF (x10^-3)=1.29, Model Scale=mobile2023.12 | 1.17 | 0.126 | — | |
| NeXt-TDNN-l(C=384, B=1)Params=5.9M, MACs=1.609G, RTF (x10^-3)=0.63, Model Scale=base2023.12 | 1.18 | 0.1208 | — | |
| EfficientTDNN-BaseParams=5.8M, MACs=1.450G, RTF (x10^-3)=1.32, Model Scale=base2023.12 | 1.2 | 0.1296 | — | |
| NeXt-TDNN-l(C=128, B=3)Params=1.6M, MACs=0.441G, RTF (x10^-3)=0.89, Model Scale=mobile2023.12 | 1.24 | 0.1334 | — | |
| ECAPA-TDNN + GRL2026.03 | 1.25 | 0.14 | 0.12 | |
| ECAPA-TDNN2026.03 | 1.34 | 0.17 | 0.11 | |
| ECAPA-TDNN (C=512)Params=6.2M, MACs=1.569G, RTF (x10^-3)=1.80, Model Scale=base2023.12 | 1.36 | 0.1464 | — | |
| NeXt-TDNN (C=192, B=1)Params=1.8M, MACs=0.478G, RTF (x10^-3)=0.63, Model Scale=mobile2023.12 | 1.39 | 0.1409 | — | |
| NeXt-TDNN-l(C=192, B=1)Params=1.6M, MACs=0.417G, RTF (x10^-3)=0.51, Model Scale=mobile2023.12 | 1.52 | 0.1497 | — | |
| EfficientTDNN-MobileParams=2.4M, MACs=0.574G, RTF (x10^-3)=1.20, Model Scale=mobile2023.12 | 1.53 | 0.1654 | — | |
| ECAPA-TDNN (C=256)Params=1.9M, MACs=0.410G, RTF (x10^-3)=1.60, Model Scale=mobile2023.12 | 1.56 | 0.1656 | — | |
| Fast ResNet-34Params=1.4M, MACs=0.675G, RTF (x10^-3)=1.67, Model Scale=mobile2023.12 | 2.18 | 0.2632 | — | |
| fwSE-ResNet-200Post-training pipeline=Model Averaging, LM-FT, CMF, AS-Norm, and QMF2026.06 | 54 | 0.047 | — | |
| ECAPA2Post-training pipeline=Model Averaging, LM-FT, CMF, AS-Norm, and QMF2026.06 | 59 | 0.056 | — | |
| Xi-VectorPost-training pipeline=Model Averaging, LM-FT, CMF, AS-Norm, and QMF2026.06 | 60 | 0.051 | — | |
| ReDimNetPost-training pipeline=Model Averaging, LM-FT, CMF, AS-Norm, and QMF2026.06 | 66 | 0.056 | — |