Trial Set
CN-Celeb
Keeps the upstream CN-Celeb evaluation trial protocol.
- Source dataset
- CN-Celeb
- Trials
- 3484292
- Protocol source
- Official protocol
- Source split
- Official evaluation protocol
Source Dataset
About CN-Celeb
CN-Celeb was built to study Chinese speaker recognition in unconstrained media conditions. The original collection contains more than 130,000 utterances from 1,000 celebrities across 11 real-world genres; the later CN-Celeb2 release expands the multi-genre collection to 3,000 speakers. The main OpenSVBench entry uses the upstream evaluation protocol, while the genre and short-duration entries are separate supplements.
- Language
- Chinese
- Original CN-Celeb
- 1,000 speakers; 130,000+ utterances
- Genres
- 11 real-world media genres
- Recording
- In-the-wild media speech
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 |
iic/eres2netv2-zh
eresv2_zh
|
Public checkpoint | 3.8243 | 0.165880 |
| #2 |
iic/campplus
campplus
|
Public checkpoint | 4.7029 | 0.224112 |
| #3 |
W2V-BERT 2.0 + MHFA (VoxCeleb2 + VoxBlink2)
Wav2Vec2-BERT
|
pengjy | 7.0671 | 0.277016 |
| #4 |
AntSpeaker/MECT-B2
antspeaker-mect-b2-vb2-full-core
|
Public checkpoint | 7.0910 | 0.240625 |
| #5 |
wespeaker/res34-cnceleb
wespeaker_r34
|
Public checkpoint | 7.4729 | 0.345407 |
| #6 |
palabraai/redimnet2-b6-vb2+vox2
redimnet2-b6-vb2vox2-lm-full-core
|
Public checkpoint | 7.8288 | 0.259349 |
| #7 |
Dual-LoRA W2V-BERT2-Adapter-MFA (TidyVoice)
duallora-w2vbert2-tidyvoice-full-core
|
shangguanqituan | 7.8964 | 0.263702 |
| #8 |
Agora Voiceprint (ResNet293)
agora_vp
|
agora_vp | 8.9045 | 0.281688 |
| #9 |
wespeaker/w2vbert2
vb2-w2vbert
|
Public checkpoint | 9.9690 | 0.300308 |
| #10 |
wespeaker/samresnet100
vb2-sam100
|
Public checkpoint | 9.9803 | 0.311502 |
| #11 |
wespeaker/res152-voxceleb
wespeaker_resnet152
|
Public checkpoint | 11.3672 | 0.399395 |
| #12 |
wespeaker/res34-voxceleb
wespeaker_resnet34_voxceleb
|
Public checkpoint | 11.9718 | 0.411595 |
| #13 |
iic/eres2net-en
eres_en
|
Public checkpoint | 12.1487 | 0.429169 |
| #14 |
palabraai/redimnet2-b6
redimnet2
|
Public checkpoint | 12.2444 | 0.378920 |
| #15 |
wespeaker/res293-voxceleb
wespeaker_resnet293
|
Public checkpoint | 12.4334 | 0.412299 |
| #16 |
iic/eres2net-large-3dspeaker
eres2net_large_3dspeaker
|
Public checkpoint | 14.0524 | 0.486731 |
| #17 |
speechbrain/ecapa
ecapa
|
Public checkpoint | 15.2177 | 0.579855 |
| #18 |
wespeaker/campplus-voxceleb
campplus_wespeaker
|
Public checkpoint | 15.7139 | 0.551833 |
| #19 |
wespeaker/ecapa1024-voxceleb
wespeaker_ecapa1024
|
Public checkpoint | 15.8209 | 0.536618 |
| #20 |
wespeaker/ecapa512-voxceleb
wespeaker_ecapa512
|
Public checkpoint | 16.3391 | 0.550287 |
| #21 |
speechbrain/xvector
xvector
|
Public checkpoint | 24.2749 | 0.826837 |
| #22 |
microsoft/wavlm-base-plus-sv
wavlm_base
|
Public checkpoint | 27.9358 | 0.916549 |
| #23 |
microsoft/unispeech-sat-base-plus-sv
unispeech_sat_base_plus
|
Public checkpoint | 29.8022 | 0.945410 |