Trial Set
VoxKnesset
Builds aging trials from the official test split and speaker age/time metadata.
- Source dataset
- VoxKnesset
- Trials
- 158312
- Protocol source
- Self-constructed protocol
- Source split
- Official VoxKnesset test split
Source Dataset
About VoxKnesset
VoxKnesset is a longitudinal Hebrew speech dataset built from Israeli parliamentary recordings. The release contains about 2,300 hours from 393 speakers, spanning 2009–2025 with some speakers represented over periods of up to 15 years. OpenSVBench uses the official test split and constructs age/time-gap trials from speaker metadata.
- Language
- Hebrew
- Scale
- About 2,300 hours; 393 speakers
- Time span
- Parliamentary recordings from 2009–2025
- Original focus
- Longitudinal speaker modeling and vocal aging
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 |
W2V-BERT 2.0 + MHFA (VoxCeleb2 + VoxBlink2)
Wav2Vec2-BERT
|
pengjy | 2.0600 | 0.091088 |
| #2 |
AntSpeaker/MECT-B2
antspeaker-mect-b2-vb2-full-core
|
Public checkpoint | 2.1800 | 0.086290 |
| #3 |
palabraai/redimnet2-b6-vb2+vox2
redimnet2-b6-vb2vox2-lm-full-core
|
Public checkpoint | 2.2933 | 0.078447 |
| #4 |
wespeaker/samresnet100
vb2-sam100
|
Public checkpoint | 2.5933 | 0.101669 |
| #5 |
wespeaker/w2vbert2
vb2-w2vbert
|
Public checkpoint | 2.6533 | 0.081689 |
| #6 |
Dual-LoRA W2V-BERT2-Adapter-MFA (TidyVoice)
duallora-w2vbert2-tidyvoice-full-core
|
shangguanqituan | 2.7267 | 0.100356 |
| #7 |
palabraai/redimnet2-b6
redimnet2
|
Public checkpoint | 3.3600 | 0.138451 |
| #8 |
wespeaker/res293-voxceleb
wespeaker_resnet293
|
Public checkpoint | 3.5733 | 0.143699 |
| #9 |
wespeaker/res152-voxceleb
wespeaker_resnet152
|
Public checkpoint | 3.7467 | 0.148597 |
| #10 |
Agora Voiceprint (ResNet293)
agora_vp
|
agora_vp | 3.7554 | 0.140025 |
| #11 |
wespeaker/res34-voxceleb
wespeaker_resnet34_voxceleb
|
Public checkpoint | 4.9242 | 0.199224 |
| #12 |
wespeaker/campplus-voxceleb
campplus_wespeaker
|
Public checkpoint | 5.0067 | 0.213777 |
| #13 |
iic/eres2net-en
eres_en
|
Public checkpoint | 5.4308 | 0.235319 |
| #14 |
wespeaker/ecapa1024-voxceleb
wespeaker_ecapa1024
|
Public checkpoint | 5.6932 | 0.252750 |
| #15 |
wespeaker/ecapa512-voxceleb
wespeaker_ecapa512
|
Public checkpoint | 6.6861 | 0.282060 |
| #16 |
speechbrain/ecapa
ecapa
|
Public checkpoint | 6.9067 | 0.325019 |
| #17 |
iic/eres2netv2-zh
eresv2_zh
|
Public checkpoint | 11.4067 | 0.527584 |
| #18 |
wespeaker/res34-cnceleb
wespeaker_r34
|
Public checkpoint | 14.3733 | 0.632640 |
| #19 |
iic/campplus
campplus
|
Public checkpoint | 15.4369 | 0.696994 |
| #20 |
iic/eres2net-large-3dspeaker
eres2net_large_3dspeaker
|
Public checkpoint | 20.2049 | 0.837278 |
| #21 |
speechbrain/xvector
xvector
|
Public checkpoint | 22.2605 | 0.834057 |
| #22 |
microsoft/wavlm-base-plus-sv
wavlm_base
|
Public checkpoint | 23.1333 | 0.940091 |
| #23 |
microsoft/unispeech-sat-base-plus-sv
unispeech_sat_base_plus
|
Public checkpoint | 27.7733 | 0.972844 |