Trial Set
TidyVoiceX2-ASV
Uses released labeled TidyVoiceX2-ASV eval A/U keys with reproducible subsampling and deterministic matched non-target completion.
Notice: This is not the original official SV trial list.
- Source dataset
- TidyVoiceX2-ASV
- Trials
- 200000
- Protocol source
- Official eval-key subset + constructed completion
- Source split
- TidyVoiceX2-ASV eval A/U
Source Dataset
About TidyVoiceX2-ASV
TidyVoice is a multilingual speaker-verification resource curated from Mozilla Common Voice, with speaker identities reviewed to reduce inconsistencies in the source corpus. TidyVoiceX focuses on language mismatch, and TidyVoiceX2-ASV is the evaluation set used by the 2026 challenge. The OpenSVBench protocol for this page is described separately above.
- Source
- Mozilla Common Voice read speech
- Focus
- Same-language and cross-language speaker verification
- TidyVoiceX
- About 40 languages in the 2026 challenge
Direct Ranking
Systems on this trial set
23 reviewed systems currently have valid results.
| Rank | System | Submitted by | Trial-Set EER ↓ | Trial-Set minDCF ↓ |
|---|---|---|---|---|
| #1 |
Dual-LoRA W2V-BERT2-Adapter-MFA (TidyVoice)
duallora-w2vbert2-tidyvoice-full-core
|
shangguanqituan | 1.6577 | 0.102286 |
| #2 |
Agora Voiceprint (ResNet293)
agora_vp
|
agora_vp | 2.3854 | 0.170770 |
| #3 |
AntSpeaker/MECT-B2
antspeaker-mect-b2-vb2-full-core
|
Public checkpoint | 2.6211 | 0.254113 |
| #4 |
W2V-BERT 2.0 + MHFA (VoxCeleb2 + VoxBlink2)
Wav2Vec2-BERT
|
pengjy | 2.6605 | 0.211953 |
| #5 |
palabraai/redimnet2-b6-vb2+vox2
redimnet2-b6-vb2vox2-lm-full-core
|
Public checkpoint | 3.4191 | 0.259714 |
| #6 |
wespeaker/w2vbert2
vb2-w2vbert
|
Public checkpoint | 4.4676 | 0.330255 |
| #7 |
wespeaker/samresnet100
vb2-sam100
|
Public checkpoint | 4.7178 | 0.362506 |
| #8 |
wespeaker/res293-voxceleb
wespeaker_resnet293
|
Public checkpoint | 4.7483 | 0.298819 |
| #9 |
palabraai/redimnet2-b6
redimnet2
|
Public checkpoint | 4.7707 | 0.339730 |
| #10 |
wespeaker/res152-voxceleb
wespeaker_resnet152
|
Public checkpoint | 4.8269 | 0.305505 |
| #11 |
iic/eres2netv2-zh
eresv2_zh
|
Public checkpoint | 5.3320 | 0.299692 |
| #12 |
iic/eres2net-en
eres_en
|
Public checkpoint | 5.5284 | 0.374254 |
| #13 |
wespeaker/res34-voxceleb
wespeaker_resnet34_voxceleb
|
Public checkpoint | 5.5532 | 0.361444 |
| #14 |
wespeaker/campplus-voxceleb
campplus_wespeaker
|
Public checkpoint | 6.1851 | 0.403050 |
| #15 |
iic/campplus
campplus
|
Public checkpoint | 6.4713 | 0.346271 |
| #16 |
wespeaker/ecapa512-voxceleb
wespeaker_ecapa512
|
Public checkpoint | 6.5083 | 0.405096 |
| #17 |
wespeaker/ecapa1024-voxceleb
wespeaker_ecapa1024
|
Public checkpoint | 6.9847 | 0.436029 |
| #18 |
wespeaker/res34-cnceleb
wespeaker_r34
|
Public checkpoint | 7.5770 | 0.460771 |
| #19 |
speechbrain/ecapa
ecapa
|
Public checkpoint | 7.6275 | 0.509746 |
| #20 |
iic/eres2net-large-3dspeaker
eres2net_large_3dspeaker
|
Public checkpoint | 8.5536 | 0.499376 |
| #21 |
speechbrain/xvector
xvector
|
Public checkpoint | 14.0989 | 0.582957 |
| #22 |
microsoft/wavlm-base-plus-sv
wavlm_base
|
Public checkpoint | 21.7152 | 0.966351 |
| #23 |
microsoft/unispeech-sat-base-plus-sv
unispeech_sat_base_plus
|
Public checkpoint | 23.2288 | 0.970581 |