Speaker Recognition on VoxCeleb Hard 1
0.0186EERProposed RecXi
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Proposed RecXiParams (Million)=7.06, Need Speaker Labels?=Yes, Need Pre-trained ASR Model?=No2023.10 | 0.0186 | 0.179 | |
| NEMOParams (Million)=15.88, Need Speaker Labels?=Yes, Need Pre-trained ASR Model?=No2023.10 | 0.019 | 0.189 | |
| NEMOParams (Million)=15.88, Need Speaker Labels?=Yes, Need Pre-trained ASR Model?=Yes2023.10 | 0.022 | 0.225 | |
| IPAParams (Million)=>60, Need Speaker Labels?=Yes, Need Pre-trained ASR Model?=Yes2023.10 | 0.0312 | — | |
| MCL-DPP-CParams (Million)=10.5, Need Speaker Labels?=Pseudo label, Need Pre-trained ASR Model?=No2023.10 | 0.0327 | — | |
| MCL-DPPParams (Million)=10.5, Need Speaker Labels?=No, Need Pre-trained ASR Model?=No2023.10 | 0.0627 | — |