OpenSVBench Scenario-driven SV leaderboard
System Detail

wespeaker/ ecapa512-voxceleb

wespeaker_ecapa512

ranked review: approved WeSpeaker ECAPA-TDNN

This page shows the global rank, scenario ranks, and trial-set results for this submission.

Global Position

#13/18

Public ranking position among reviewed full-core submissions.

Scenario-Macro EER
14.3120
Scenario-Macro minDCF
0.541141
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/ecapa512-voxceleb
  • Source: WeSpeaker
  • Architecture: ECAPA-TDNN
  • Submitted alias: wespeaker-voxceleb-ecapa-tdnn512-LM
  • Created at: 2026-05-29T14:47:10.548863+00:00
Training And Links

Training data and references

Higher-Ranked Scenarios

Scenario ranks above the global position

Show 3 supporting trial sets
  • Lombard Grid Lombard: #7 on its trial-set ranking.
  • GLOBE: #7 on its trial-set ranking.
  • ESD: #8 on its trial-set ranking.
Lower-Ranked Scenarios

Scenario ranks below the global position

Show 3 supporting trial sets
  • 3D-Speaker Distance: #15 on its trial-set ranking.
  • Whisper40 Whisper: #15 on its trial-set ranking.
  • CN-Celeb: #15 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.
#11/18 Needs work
Speaker aging and time gaps 2.7556 EER from leader
4.8252
0.212812 minDCF
Cross-Lingual Robustness
How well speaker identity survives enrollment-test language mismatch.
#11/18 Needs work
Language mismatch 2.0406 EER from leader
6.5083
0.405096 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.
#11/18 Needs work
Noise and reverberation 5.0360 EER from leader
7.6160
0.264660 minDCF
Speaking-Style Robustness
Whether the model can preserve identity across emotion-driven change, whispered speech, and noise-induced Lombard speaking style.
#12/18 Needs work
Speaking style shift 4.3234 EER from leader
7.1128
0.367138 minDCF
Short-Duration Robustness
How much performance holds up when speech evidence is limited by duration.
#12/18 Needs work
Short-duration speech 4.0397 EER from leader
16.5541
0.604686 minDCF
Overlap Robustness
How well speaker identity survives light, mid, and heavy overlap in both meeting and domestic recordings.
#13/18 Needs work
Overlapping speakers 4.8106 EER from leader
14.9489
0.650355 minDCF
Distance Robustness
How much performance changes across meeting and domestic distance mismatch.
#13/18 Needs work
Distance mismatch 6.7809 EER from leader
16.0447
0.664732 minDCF
Accent / Dialect Robustness
How reliably the model tracks identity across accent and dialect mismatch.
#13/18 Needs work
Accent and dialect variation 4.8977 EER from leader
25.3328
0.762541 minDCF
In-The-Wild Robustness
How strong the model is on unconstrained celebrity and media speech across official CN-Celeb and VoxCeleb protocols.
#14/18 Needs work
Open-domain media speech 3.7369 EER from leader
8.9203
0.324306 minDCF
Channel / Device Robustness
How resilient the model is to device and channel mismatch.
#14/18 Needs work
Device and channel variation 12.4039 EER from leader
18.7142
0.846298 minDCF
Genre-Shift Robustness
Whether performance holds when CN-Celeb enrollment and test speech come from different source genres.
#14/18 Needs work
Source-genre variation 16.5825 EER from leader
30.8550
0.849922 minDCF
Variant Compare

Compare ECAPA-TDNN variants

Expand this section to compare checkpoints in the same architecture group by source, training data, training setup, and leaderboard result.

Show
Variant Source Training Data Training Setup Global Rank Macro EER Macro minDCF Open
speechbrain/ecapa SpeechBrain VoxCeleb1 + VoxCeleb2 training data SpeechBrain ECAPA-TDNN release with attentive statistical pooling and Additive Margin Softmax loss. #10
ranked
13.5461 0.543660 Open
wespeaker/ecapa1024-voxceleb WeSpeaker VoxCeleb2 dev, 5,994 speakers ECAPA-TDNN GLOB c1024 with ASTP pooling, 192-d embedding, ArcMargin, 150-epoch training, speed perturbation, and MUSAN/RIRS augmentation. #11
ranked
14.0835 0.534111 Open
wespeaker/ecapa512-voxceleb
Current
WeSpeaker VoxCeleb2 dev, 5,994 speakers ECAPA-TDNN GLOB c512 with ASTP pooling, 192-d embedding, ArcMargin, large-margin fine-tuning, speed perturbation, and MUSAN/RIRS augmentation. #13
ranked
14.3120 0.541141 Open
Trial-Set Results

Raw ranking by trial set

Expand this section to inspect the detailed trial-set rankings.

Show
Trial Set Rank Scenarios Trials Score
TidyVoiceX2-ASV
TidyVoiceX2-ASV
#11/18
Cross-lingual
200000
6.5083
0.405096 minDCF
HI-MIA
HI-MIA
#14/18
Short-duration
660000
8.5340
0.404212 minDCF
GSC Short
Google Speech Commands
#9/18
Short-duration
220000
12.8770
0.644885 minDCF
GLOBE
GLOBE
#7/18
Accent/dialect
56848
25.4257
0.525755 minDCF
CN-Celeb
CN-Celeb
#15/18
In-the-wild
3484292
16.3391
0.550287 minDCF
CN-Celeb Genre
CN-Celeb
#14/18
Genre shift
440000
30.8550
0.849922 minDCF
CN-Celeb Short
CN-Celeb
#14/18
Short-duration
546964
29.6374
0.854863 minDCF
VoxCeleb1-O
VoxCeleb1
#11/18
In-the-wild
37611
1.0371
0.085403 minDCF
VoxCeleb1-E
VoxCeleb1
#11/18
In-the-wild
579818
1.2104
0.077313 minDCF
VoxCeleb1-H
VoxCeleb1
#11/18
In-the-wild
550894
2.2570
0.132259 minDCF
VoxCeleb Short
VoxCeleb1
#10/18
Short-duration
394724
15.1680
0.514784 minDCF
3D-Speaker Device
3D-Speaker
#14/18
Channel/device
180000
25.3867
0.995540 minDCF
3D-Speaker Distance
3D-Speaker
#15/18
Distance
175163
25.4467
0.989464 minDCF
3D-Speaker Dialect
3D-Speaker
#13/18
Accent/dialect
180000
25.2400
0.999327 minDCF
FFSVC 2022 Cross-Channel
FFSVC 2022
#12/18
Channel/device
72000
12.0417
0.697056 minDCF
FFSVC 2022 Cross-Domain
FFSVC 2022
#12/18
Distance
66546
12.1783
0.703849 minDCF
Whisper40 Whisper
Whisper40
#15/18
Speaking style
17600
16.6250
0.780062 minDCF
Lombard Grid Lombard
Lombard Grid
#7/18
Speaking style
29524
0.2235
0.015499 minDCF
VOiCES Noise/Reverb
VOiCES
#11/18
Noise/reverb
55000
7.6160
0.264660 minDCF
CHiME-6 Domestic Far-Field
CHiME-6
#11/18
Distance
36487
15.1040
0.585680 minDCF
CHiME-6 Overlap
CHiME-6
#11/18
Overlap
39600
18.2778
0.716417 minDCF
ESD
ESD
#8/18
Speaking style
437408
4.4900
0.305853 minDCF
AliMeeting Near/Far
AliMeeting
#15/18
Distance
220000
11.4500
0.379935 minDCF
AliMeeting Overlap
AliMeeting
#15/18
Overlap
165000
11.6200
0.584293 minDCF
VoxKnesset
VoxKnesset
#10/18
Aging
158312
6.6861
0.282060 minDCF
VoxPopuli Aging
VoxPopuli
#11/18
Aging
146575
2.9644
0.143565 minDCF