Trial Set
VoxPopuli Aging
Builds English-only aging trials from European Parliament recording dates parsed from audio_id.
- Source dataset
- VoxPopuli
- Trials
- 146575
- Protocol source
- Self-constructed protocol
- Source split
- VoxPopuli English train split
Source Dataset
About VoxPopuli
VoxPopuli was collected from European Parliament recordings for multilingual speech representation learning and speech technology. The paper reports 400,000 hours of unlabelled speech in 23 languages, alongside transcribed subsets. OpenSVBench uses only selected English utterances from the train split and constructs its own cross-time speaker-verification trials using recording dates.
- Source
- European Parliament recordings
- Unlabelled corpus
- 400,000 hours across 23 languages
- Additional data
- Transcribed speech and aligned interpretations
- OpenSVBench subset
- Selected English train-split utterances
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 |
wespeaker/w2vbert2
vb2-w2vbert
|
Public checkpoint | 1.5159 | 0.024105 |
| #2 |
palabraai/redimnet2-b6-vb2+vox2
redimnet2-b6-vb2vox2-lm-full-core
|
Public checkpoint | 1.5159 | 0.026206 |
| #3 |
AntSpeaker/MECT-B2
antspeaker-mect-b2-vb2-full-core
|
Public checkpoint | 1.5235 | 0.026056 |
| #4 |
W2V-BERT 2.0 + MHFA (VoxCeleb2 + VoxBlink2)
Wav2Vec2-BERT
|
pengjy | 1.5235 | 0.030244 |
| #5 |
palabraai/redimnet2-b6
redimnet2
|
Public checkpoint | 1.5460 | 0.037846 |
| #6 |
wespeaker/samresnet100
vb2-sam100
|
Public checkpoint | 1.5460 | 0.035895 |
| #7 |
Dual-LoRA W2V-BERT2-Adapter-MFA (TidyVoice)
duallora-w2vbert2-tidyvoice-full-core
|
shangguanqituan | 1.6060 | 0.030296 |
| #8 |
Agora Voiceprint (ResNet293)
agora_vp
|
agora_vp | 1.6210 | 0.049651 |
| #9 |
wespeaker/res293-voxceleb
wespeaker_resnet293
|
Public checkpoint | 1.7411 | 0.070206 |
| #10 |
wespeaker/res152-voxceleb
wespeaker_resnet152
|
Public checkpoint | 1.7486 | 0.073433 |
| #11 |
iic/eres2net-en
eres_en
|
Public checkpoint | 1.8537 | 0.074717 |
| #12 |
wespeaker/res34-voxceleb
wespeaker_resnet34_voxceleb
|
Public checkpoint | 2.0788 | 0.092901 |
| #13 |
speechbrain/ecapa
ecapa
|
Public checkpoint | 2.1989 | 0.111452 |
| #14 |
wespeaker/campplus-voxceleb
campplus_wespeaker
|
Public checkpoint | 2.2071 | 0.107415 |
| #15 |
wespeaker/ecapa1024-voxceleb
wespeaker_ecapa1024
|
Public checkpoint | 2.3715 | 0.110394 |
| #16 |
wespeaker/ecapa512-voxceleb
wespeaker_ecapa512
|
Public checkpoint | 2.9644 | 0.143565 |
| #17 |
iic/eres2netv2-zh
eresv2_zh
|
Public checkpoint | 7.1662 | 0.466934 |
| #18 |
speechbrain/xvector
xvector
|
Public checkpoint | 8.6679 | 0.488593 |
| #19 |
iic/campplus
campplus
|
Public checkpoint | 9.2383 | 0.553561 |
| #20 |
microsoft/wavlm-base-plus-sv
wavlm_base
|
Public checkpoint | 9.7786 | 0.663805 |
| #21 |
wespeaker/res34-cnceleb
wespeaker_r34
|
Public checkpoint | 9.8837 | 0.638041 |
| #22 |
microsoft/unispeech-sat-base-plus-sv
unispeech_sat_base_plus
|
Public checkpoint | 10.9824 | 0.743985 |
| #23 |
iic/eres2net-large-3dspeaker
eres2net_large_3dspeaker
|
Public checkpoint | 18.2139 | 0.992315 |