System Detail
wespeaker/ campplus-voxceleb
campplus_wespeaker
This page shows the global rank, scenario ranks, and trial-set results for this submission.
Global Position
#9/18
Public ranking position among reviewed full-core submissions.
Scenario-Macro EER
13.4165
Scenario-Macro minDCF
0.520675
Coverage
26/26
0 scenarios ranked #1
0 scenarios in top 3
Public Listing
Ranked Publicly
This full-core result is approved and included in the public ranking.
Model Provenance
Source and architecture
- Displayed name:
wespeaker/campplus-voxceleb - Source: WeSpeaker
- Architecture: CAMPPlus
- Submitted alias:
wespeaker-voxceleb-campplus-LM - Created at:
2026-05-29T14:20:28.222436+00:00
Training And Links
Training data and references
- Training data: VoxCeleb2 dev
- Training setup: CAMPPlus with TSTP pooling, ArcMargin large-margin fine-tuning, and MUSAN/RIRS augmentation.
- Submission mode:
full-core - Paper: CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking
Higher-Ranked Scenarios
Scenario ranks above the global position
Show 3 supporting trial sets
- VoxCeleb1-O: #6 on its trial-set ranking.
- VoxCeleb Short: #6 on its trial-set ranking.
- CHiME-6 Overlap: #6 on its trial-set ranking.
Lower-Ranked Scenarios
Scenario ranks below the global position
Show 3 supporting trial sets
- CN-Celeb Genre: #13 on its trial-set ranking.
- GSC Short: #13 on its trial-set ranking.
- CN-Celeb: #13 on its trial-set ranking.
Scenario Rankings
Full ranking across scenarios
This table shows where the model sits on each scenario, using source-balanced scenario scores and the linked trial sets as evidence.
| Scenario | Rank | Lens | Evidence | Score |
|---|---|---|---|---|
|
Aging Robustness
How stable identity representations remain across age-derived and longitudinal recording gaps.
|
#7/18
Competitive
|
Speaker aging and time gaps
1.5372 EER from leader
|
3.6069
0.160596 minDCF
|
|
|
Overlap Robustness
How well speaker identity survives light, mid, and heavy overlap in both meeting and domestic recordings.
|
#8/18
Competitive
|
Overlapping speakers
3.9432 EER from leader
|
14.0816
0.622128 minDCF
|
|
|
Cross-Lingual Robustness
How well speaker identity survives enrollment-test language mismatch.
|
#9/18
Competitive
|
Language mismatch
1.7175 EER from leader
|
6.1851
0.403050 minDCF
|
|
|
Speaking-Style Robustness
Whether the model can preserve identity across emotion-driven change, whispered speech, and noise-induced Lombard speaking style.
|
#9/18
Competitive
|
Speaking style shift
3.5680 EER from leader
|
6.3574
0.358438 minDCF
|
|
|
Noise / Reverb Robustness
How reliably the model preserves identity when room acoustics, distractor noise, and microphone placement deviate from an easier in-corpus reference condition.
|
#9/18
Competitive
|
Noise and reverberation
3.8800 EER from leader
|
6.4600
0.220820 minDCF
|
|
|
Distance Robustness
How much performance changes across meeting and domestic distance mismatch.
|
#11/18
Needs work
|
Distance mismatch
5.4153 EER from leader
|
14.6792
0.634129 minDCF
|
|
|
Short-Duration Robustness
How much performance holds up when speech evidence is limited by duration.
|
#11/18
Needs work
|
Short-duration speech
3.8350 EER from leader
|
16.3494
0.638979 minDCF
|
|
|
Accent / Dialect Robustness
How reliably the model tracks identity across accent and dialect mismatch.
|
#11/18
Needs work
|
Accent and dialect variation
3.4931 EER from leader
|
23.9283
0.721471 minDCF
|
|
|
In-The-Wild Robustness
How strong the model is on unconstrained celebrity and media speech across official CN-Celeb and VoxCeleb protocols.
|
#12/18
Needs work
|
Open-domain media speech
3.2202 EER from leader
|
8.4036
0.311533 minDCF
|
|
|
Channel / Device Robustness
How resilient the model is to device and channel mismatch.
|
#12/18
Needs work
|
Device and channel variation
11.5697 EER from leader
|
17.8800
0.826833 minDCF
|
|
|
Genre-Shift Robustness
Whether performance holds when CN-Celeb enrollment and test speech come from different source genres.
|
#13/18
Needs work
|
Source-genre variation
15.3772 EER from leader
|
29.6497
0.829445 minDCF
|
Variant Compare
Compare CAMPPlus variants
Expand this section to compare checkpoints in the same architecture group by source, training data, training setup, and leaderboard result.
Show
Compare CAMPPlus variants
Expand this section to compare checkpoints in the same architecture group by source, training data, training setup, and leaderboard result.
| Variant | Source | Training Data | Training Setup | Global Rank | Macro EER | Macro minDCF | Open |
|---|---|---|---|---|---|---|---|
|
wespeaker/campplus-voxceleb
Current
|
WeSpeaker | VoxCeleb2 dev | CAMPPlus with TSTP pooling, ArcMargin large-margin fine-tuning, and MUSAN/RIRS augmentation. |
#9
ranked
|
13.4165 | 0.520675 | Open |
| iic/campplus | IIC | Large Chinese speaker corpus, about 200k speakers | Official ModelScope CAMPPlus release. |
#15
ranked
|
15.1677 | 0.590178 | Open |
Trial-Set Results
Raw ranking by trial set
Expand this section to inspect the detailed trial-set rankings.
Show
Raw ranking by trial set
Expand this section to inspect the detailed trial-set rankings.
| Trial Set | Rank | Scenarios | Trials | Score |
|---|---|---|---|---|
|
TidyVoiceX2-ASV
TidyVoiceX2-ASV
|
#9/18
|
Cross-lingual
|
200000 |
6.1851
0.403050 minDCF
|
|
HI-MIA
HI-MIA
|
#13/18
|
Short-duration
|
660000 |
7.9797
0.395343 minDCF
|
|
GSC Short
Google Speech Commands
|
#13/18
|
Short-duration
|
220000 |
16.4345
0.764210 minDCF
|
|
GLOBE
GLOBE
|
#10/18
|
Accent/dialect
|
56848 |
25.6966
0.530070 minDCF
|
|
CN-Celeb
CN-Celeb
|
#13/18
|
In-the-wild
|
3484292 |
15.7139
0.551833 minDCF
|
|
CN-Celeb Genre
CN-Celeb
|
#13/18
|
Genre shift
|
440000 |
29.6497
0.829445 minDCF
|
|
CN-Celeb Short
CN-Celeb
|
#12/18
|
Short-duration
|
546964 |
27.4153
0.854569 minDCF
|
|
VoxCeleb1-O
VoxCeleb1
|
#6/18
|
In-the-wild
|
37611 |
0.7180
0.061049 minDCF
|
|
VoxCeleb1-E
VoxCeleb1
|
#7/18
|
In-the-wild
|
579818 |
0.8789
0.054292 minDCF
|
|
VoxCeleb1-H
VoxCeleb1
|
#8/18
|
In-the-wild
|
550894 |
1.6832
0.098356 minDCF
|
|
VoxCeleb Short
VoxCeleb1
|
#6/18
|
Short-duration
|
394724 |
13.5682
0.541793 minDCF
|
|
3D-Speaker Device
3D-Speaker
|
#12/18
|
Channel/device
|
180000 |
23.4600
0.938000 minDCF
|
|
3D-Speaker Distance
3D-Speaker
|
#11/18
|
Distance
|
175163 |
22.2628
0.902270 minDCF
|
|
3D-Speaker Dialect
3D-Speaker
|
#11/18
|
Accent/dialect
|
180000 |
22.1600
0.912873 minDCF
|
|
FFSVC 2022 Cross-Channel
FFSVC 2022
|
#13/18
|
Channel/device
|
72000 |
12.3000
0.715667 minDCF
|
|
FFSVC 2022 Cross-Domain
FFSVC 2022
|
#13/18
|
Distance
|
66546 |
12.4278
0.723857 minDCF
|
|
Whisper40 Whisper
Whisper40
|
#11/18
|
Speaking style
|
17600 |
14.0000
0.689750 minDCF
|
|
Lombard Grid Lombard
Lombard Grid
|
#11/18
|
Speaking style
|
29524 |
0.4098
0.039531 minDCF
|
|
VOiCES Noise/Reverb
VOiCES
|
#9/18
|
Noise/reverb
|
55000 |
6.4600
0.220820 minDCF
|
|
CHiME-6 Domestic Far-Field
CHiME-6
|
#8/18
|
Distance
|
36487 |
13.0540
0.549864 minDCF
|
|
CHiME-6 Overlap
CHiME-6
|
#6/18
|
Overlap
|
39600 |
16.9444
0.668250 minDCF
|
|
ESD
ESD
|
#10/18
|
Speaking style
|
437408 |
4.6625
0.346034 minDCF
|
|
AliMeeting Near/Far
AliMeeting
|
#13/18
|
Distance
|
220000 |
10.9720
0.360525 minDCF
|
|
AliMeeting Overlap
AliMeeting
|
#12/18
|
Overlap
|
165000 |
11.2187
0.576007 minDCF
|
|
VoxKnesset
VoxKnesset
|
#7/18
|
Aging
|
158312 |
5.0067
0.213777 minDCF
|
|
VoxPopuli Aging
VoxPopuli
|
#9/18
|
Aging
|
146575 |
2.2071
0.107415 minDCF
|