System Detail
wespeaker/ w2vbert2
vb2-w2vbert
This page shows the global rank, scenario ranks, and trial-set results for this submission.
Global Position
#1/18
Public ranking position among reviewed full-core submissions.
Scenario-Macro EER
9.9604
Scenario-Macro minDCF
0.360767
Coverage
26/26
7 scenarios ranked #1
9 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/w2vbert2 - Source: WeSpeaker
- Architecture: w2v-BERT 2.0
- Submitted alias:
voxceleb_voxblink2_w2v_bert2_lora_adapterMFA_lm - Created at:
2026-05-29T14:24:45.970729+00:00
Training And Links
Training data and references
- Training data: VoxCeleb + VoxBlink2
- Training setup: W2V-BERT2.0-MFA-LM from WeSpeaker's three-stage recipe: Frozen (LoRA) => Joint ft => Joint lmft.
- Submission mode:
full-core - Paper: Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruning
Higher-Ranked Scenarios
Scenario ranks above the global position
Show 3 supporting trial sets
- VoxCeleb1-O: #1 on its trial-set ranking.
- VoxCeleb1-E: #1 on its trial-set ranking.
- VoxCeleb1-H: #1 on its trial-set ranking.
Lower-Ranked Scenarios
Scenario ranks below the global position
Show 3 supporting trial sets
- FFSVC 2022 Cross-Domain: #10 on its trial-set ranking.
- FFSVC 2022 Cross-Channel: #10 on its trial-set ranking.
- CN-Celeb Short: #8 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 |
|---|---|---|---|---|
|
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.
|
#1/18
Leader
|
Noise and reverberation
0.0000 EER from leader
|
2.5800
0.074040 minDCF
|
|
|
Speaking-Style Robustness
Whether the model can preserve identity across emotion-driven change, whispered speech, and noise-induced Lombard speaking style.
|
#1/18
Leader
|
Speaking style shift
0.0000 EER from leader
|
2.7895
0.157223 minDCF
|
|
|
Cross-Lingual Robustness
How well speaker identity survives enrollment-test language mismatch.
|
#1/18
Leader
|
Language mismatch
0.0000 EER from leader
|
4.4676
0.330255 minDCF
|
|
|
In-The-Wild Robustness
How strong the model is on unconstrained celebrity and media speech across official CN-Celeb and VoxCeleb protocols.
|
#1/18
Leader
|
Open-domain media speech
0.0000 EER from leader
|
5.1834
0.162046 minDCF
|
|
|
Overlap Robustness
How well speaker identity survives light, mid, and heavy overlap in both meeting and domestic recordings.
|
#1/18
Leader
|
Overlapping speakers
0.0000 EER from leader
|
10.1383
0.467346 minDCF
|
|
|
Short-Duration Robustness
How much performance holds up when speech evidence is limited by duration.
|
#1/18
Leader
|
Short-duration speech
0.0000 EER from leader
|
12.5144
0.441680 minDCF
|
|
|
Accent / Dialect Robustness
How reliably the model tracks identity across accent and dialect mismatch.
|
#1/18
Leader
|
Accent and dialect variation
0.0000 EER from leader
|
20.4352
0.641166 minDCF
|
|
|
Aging Robustness
How stable identity representations remain across age-derived and longitudinal recording gaps.
|
#2/18
Top 3
|
Speaker aging and time gaps
0.0150 EER from leader
|
2.0846
0.052897 minDCF
|
|
|
Distance Robustness
How much performance changes across meeting and domestic distance mismatch.
|
#2/18
Top 3
|
Distance mismatch
0.9246 EER from leader
|
10.1885
0.403238 minDCF
|
|
|
Channel / Device Robustness
How resilient the model is to device and channel mismatch.
|
#4/18
Competitive
|
Device and channel variation
6.9525 EER from leader
|
13.2628
0.581970 minDCF
|
|
|
Genre-Shift Robustness
Whether performance holds when CN-Celeb enrollment and test speech come from different source genres.
|
#6/18
Competitive
|
Source-genre variation
11.6475 EER from leader
|
25.9200
0.656577 minDCF
|
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
|
#1/18
|
Cross-lingual
|
200000 |
4.4676
0.330255 minDCF
|
|
HI-MIA
HI-MIA
|
#8/18
|
Short-duration
|
660000 |
7.0400
0.349597 minDCF
|
|
GSC Short
Google Speech Commands
|
#2/18
|
Short-duration
|
220000 |
6.0250
0.388025 minDCF
|
|
GLOBE
GLOBE
|
#1/18
|
Accent/dialect
|
56848 |
24.5937
0.512152 minDCF
|
|
CN-Celeb
CN-Celeb
|
#4/18
|
In-the-wild
|
3484292 |
9.9690
0.300308 minDCF
|
|
CN-Celeb Genre
CN-Celeb
|
#6/18
|
Genre shift
|
440000 |
25.9200
0.656577 minDCF
|
|
CN-Celeb Short
CN-Celeb
|
#8/18
|
Short-duration
|
546964 |
25.9130
0.658933 minDCF
|
|
VoxCeleb1-O
VoxCeleb1
|
#1/18
|
In-the-wild
|
37611 |
0.1489
0.010954 minDCF
|
|
VoxCeleb1-E
VoxCeleb1
|
#1/18
|
In-the-wild
|
579818 |
0.3146
0.018750 minDCF
|
|
VoxCeleb1-H
VoxCeleb1
|
#1/18
|
In-the-wild
|
550894 |
0.7298
0.041650 minDCF
|
|
VoxCeleb Short
VoxCeleb1
|
#2/18
|
Short-duration
|
394724 |
11.0796
0.370165 minDCF
|
|
3D-Speaker Device
3D-Speaker
|
#2/18
|
Channel/device
|
180000 |
15.3867
0.634773 minDCF
|
|
3D-Speaker Distance
3D-Speaker
|
#3/18
|
Distance
|
175163 |
16.0613
0.619447 minDCF
|
|
3D-Speaker Dialect
3D-Speaker
|
#2/18
|
Accent/dialect
|
180000 |
16.2767
0.770180 minDCF
|
|
FFSVC 2022 Cross-Channel
FFSVC 2022
|
#10/18
|
Channel/device
|
72000 |
11.1389
0.529167 minDCF
|
|
FFSVC 2022 Cross-Domain
FFSVC 2022
|
#10/18
|
Distance
|
66546 |
11.3097
0.539530 minDCF
|
|
Whisper40 Whisper
Whisper40
|
#1/18
|
Speaking style
|
17600 |
5.8125
0.291250 minDCF
|
|
Lombard Grid Lombard
Lombard Grid
|
#2/18
|
Speaking style
|
29524 |
0.0559
0.005104 minDCF
|
|
VOiCES Noise/Reverb
VOiCES
|
#1/18
|
Noise/reverb
|
55000 |
2.5800
0.074040 minDCF
|
|
CHiME-6 Domestic Far-Field
CHiME-6
|
#1/18
|
Distance
|
36487 |
6.6928
0.260295 minDCF
|
|
CHiME-6 Overlap
CHiME-6
|
#1/18
|
Overlap
|
39600 |
12.3500
0.603472 minDCF
|
|
ESD
ESD
|
#1/18
|
Speaking style
|
437408 |
2.5000
0.175313 minDCF
|
|
AliMeeting Near/Far
AliMeeting
|
#3/18
|
Distance
|
220000 |
6.6900
0.193680 minDCF
|
|
AliMeeting Overlap
AliMeeting
|
#4/18
|
Overlap
|
165000 |
7.9267
0.331220 minDCF
|
|
VoxKnesset
VoxKnesset
|
#2/18
|
Aging
|
158312 |
2.6533
0.081689 minDCF
|
|
VoxPopuli Aging
VoxPopuli
|
#1/18
|
Aging
|
146575 |
1.5159
0.024105 minDCF
|