System Detail
palabraai/redimnet2-b6
redimnet2
Submitted by: Public checkpoint
- Global position
- #10 / 25
- Scenario-macro EER
- 10.5277
- Scenario-macro minDCF
- 0.419432
- Trial-set coverage
- 26 / 26
- Scenario top-three
- 0
Publicly ranked
This result is included in the reviewed public ranking.
Model Provenance
Source and architecture
- Displayed name:
palabraai/redimnet2-b6 - Submitted by: Public checkpoint
- Metadata: OpenSVBench model record
- Source: PalabraAI
- Architecture: ReDimNet2-B6
- Model family: ReDimNet2
- Submitted alias:
redimnet2_b6_lm - Created at:
2026-05-29T14:38:17.385092+00:00
Training And Links
Training data and references
- Training data: VoxCeleb2 dev
- Training setup: ReDimNet2-B6 speaker-verification recipe: 80-dimensional mean-normalized log-Mel filterbanks (25 ms window, 10 ms shift), a time-pooled dimension-reshaping backbone with 192-dimensional embeddings, 2-second random crops, MUSAN/RIR augmentation, and 0.9/1.1 speed perturbation during SphereFace2-C training with margin warm-up. Large-margin fine-tuning uses 6-second segments without speed perturbation, fixed margin 0.3, and five epochs with exponential learning-rate decay. The public release reports 12.3M parameters and 13.05 GMACs.
- Score processing: None
- Submission mode:
full-core - Model source: Open link
- Paper: ReDimNet2: Scaling Speaker Verification via Time-Pooled Dimension Reshaping
Higher-Ranked Scenarios
Scenario ranks above the global position
Show 3 supporting trial sets
- VoxCeleb Short: #6 on its trial-set ranking.
- VoxPopuli Aging: #7 on its trial-set ranking.
- VoxCeleb1-O: #8 on its trial-set ranking.
Lower-Ranked Scenarios
Scenario ranks below the global position
Show 3 supporting trial sets
- AliMeeting Near/Far: #18 on its trial-set ranking.
- CN-Celeb: #17 on its trial-set ranking.
- GSC Short: #16 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.
|
#8/25
Competitive
|
Noise and reverberation
0.8600 EER from leader
|
3.1200
0.114220 minDCF
|
|
|
Aging Robustness
How stable identity representations remain across age-derived and longitudinal recording gaps.
|
#9/25
Competitive
|
Speaker aging and time gaps
0.6613 EER from leader
|
2.4530
0.088149 minDCF
|
|
|
Overlap Robustness
How well speaker identity survives light, mid, and heavy overlap in both meeting and domestic recordings.
|
#10/25
Competitive
|
Overlapping speakers
3.0064 EER from leader
|
10.6981
0.524446 minDCF
|
|
|
Accent / Dialect Robustness
How reliably the model tracks identity across accent and dialect mismatch.
|
#10/25
Competitive
|
Accent and dialect variation
5.3715 EER from leader
|
21.1330
0.660821 minDCF
|
|
|
Distance Robustness
How much performance changes across meeting and domestic distance mismatch.
|
#11/25
Competitive
|
Distance mismatch
6.3857 EER from leader
|
11.0799
0.472944 minDCF
|
|
|
Channel / Device Robustness
How resilient the model is to device and channel mismatch.
|
#11/25
Competitive
|
Device and channel variation
9.0092 EER from leader
|
12.9753
0.641859 minDCF
|
|
|
Short-Duration Robustness
How much performance holds up when speech evidence is limited by duration.
|
#11/25
Competitive
|
Short-duration speech
4.6536 EER from leader
|
13.2481
0.531421 minDCF
|
|
|
Cross-Lingual Robustness
How well speaker identity survives enrollment-test language mismatch.
|
#12/25
Competitive
|
Language mismatch
3.1131 EER from leader
|
4.7707
0.339730 minDCF
|
|
|
Speaking-Style Robustness
Whether the model can preserve identity across emotion-driven change, whispered speech, and noise-induced Lombard speaking style.
|
#13/25
Competitive
|
Speaking style shift
2.5336 EER from leader
|
4.4502
0.291976 minDCF
|
|
|
In-The-Wild Robustness
How strong the model is on unconstrained celebrity and media speech across official CN-Celeb and VoxCeleb protocols.
|
#13/25
Competitive
|
Open-domain media speech
4.0355 EER from leader
|
6.4216
0.208137 minDCF
|
|
|
Genre-Shift Robustness
Whether performance holds when CN-Celeb enrollment and test speech come from different source genres.
|
#13/25
Competitive
|
Source-genre variation
12.2150 EER from leader
|
25.4550
0.740052 minDCF
|
Variant Compare
Compare ReDimNet2 variants
Compare the family variants on the overall board, a Scenario, or a Trial Set.
Show
Variant Compare
Compare ReDimNet2 variants
Compare the family variants on the overall board, a Scenario, or a Trial Set.
| Variant | Submitted by | Source | Training Data | Training Setup | Rank | EER | minDCF | Open |
|---|---|---|---|---|---|---|---|---|
|
palabraai/redimnet2-b6-vb2+vox2
ReDimNet2-B6
|
Public checkpoint | PalabraAI | VoxCeleb2 dev + VoxBlink2 | ReDimNet2-B6 speaker-verification recipe: 80-dimensional mean-normalized log-Mel filterbanks (25 ms window, 10 ms shift), a time-pooled dimension-reshaping backbone with 192-dimensional embeddings, 2-second random crops, MUSAN/RIR augmentation, and 0.9/1.1 speed perturbation during SphereFace2-C training with margin warm-up. Large-margin fine-tuning uses 6-second segments without speed perturbation, fixed margin 0.3, and five epochs with exponential learning-rate decay. This checkpoint is the extended VoxCeleb2 + VoxBlink2 release; the public release reports 12.3M parameters and 13.05 GMACs. | #8 | 9.1442 | 0.324160 | Open |
|
palabraai/redimnet2-b6
ReDimNet2-B6
Current
|
Public checkpoint | PalabraAI | VoxCeleb2 dev | ReDimNet2-B6 speaker-verification recipe: 80-dimensional mean-normalized log-Mel filterbanks (25 ms window, 10 ms shift), a time-pooled dimension-reshaping backbone with 192-dimensional embeddings, 2-second random crops, MUSAN/RIR augmentation, and 0.9/1.1 speed perturbation during SphereFace2-C training with margin warm-up. Large-margin fine-tuning uses 6-second segments without speed perturbation, fixed margin 0.3, and five epochs with exponential learning-rate decay. The public release reports 12.3M parameters and 13.05 GMACs. | #10 | 10.5277 | 0.419432 | 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
|
#12/25
|
Cross-lingual
|
200000 |
4.7707
0.339730 minDCF
|
|
HI-MIA
HI-MIA
|
#9/25
|
Short-duration
|
660000 |
5.7113
0.276288 minDCF
|
|
GSC Short
Google Speech Commands
|
#16/25
|
Short-duration
|
220000 |
12.3950
0.640440 minDCF
|
|
GLOBE
GLOBE
|
#8/25
|
Accent/dialect
|
56848 |
25.0193
0.533495 minDCF
|
|
CN-Celeb
CN-Celeb
|
#17/25
|
In-the-wild
|
3484292 |
12.2444
0.378920 minDCF
|
|
CN-Celeb Genre
CN-Celeb
|
#13/25
|
Genre shift
|
440000 |
25.4550
0.740052 minDCF
|
|
CN-Celeb Short
CN-Celeb
|
#11/25
|
Short-duration
|
546964 |
24.2213
0.769876 minDCF
|
|
VoxCeleb1-O
VoxCeleb1
|
#8/25
|
In-the-wild
|
37611 |
0.2871
0.019358 minDCF
|
|
VoxCeleb1-E
VoxCeleb1
|
#9/25
|
In-the-wild
|
579818 |
0.5198
0.031606 minDCF
|
|
VoxCeleb1-H
VoxCeleb1
|
#10/25
|
In-the-wild
|
550894 |
0.9892
0.061095 minDCF
|
|
VoxCeleb Short
VoxCeleb1
|
#6/25
|
Short-duration
|
394724 |
10.6649
0.439079 minDCF
|
|
3D-Speaker Device
3D-Speaker
|
#11/25
|
Channel/device
|
180000 |
17.2700
0.778607 minDCF
|
|
3D-Speaker Distance
3D-Speaker
|
#13/25
|
Distance
|
175163 |
17.6447
0.753012 minDCF
|
|
3D-Speaker Dialect
3D-Speaker
|
#11/25
|
Accent/dialect
|
180000 |
17.2467
0.788147 minDCF
|
|
FFSVC 2022 Cross-Channel
FFSVC 2022
|
#10/25
|
Channel/device
|
72000 |
8.6806
0.505111 minDCF
|
|
FFSVC 2022 Cross-Domain
FFSVC 2022
|
#11/25
|
Distance
|
66546 |
8.8886
0.517318 minDCF
|
|
Whisper40 Whisper
Whisper40
|
#15/25
|
Speaking style
|
17600 |
10.1875
0.646312 minDCF
|
|
Lombard Grid Lombard
Lombard Grid
|
#12/25
|
Speaking style
|
29524 |
0.0782
0.007675 minDCF
|
|
VOiCES Noise/Reverb
VOiCES
|
#8/25
|
Noise/reverb
|
55000 |
3.1200
0.114220 minDCF
|
|
CHiME-6 Domestic Far-Field
CHiME-6
|
#11/25
|
Distance
|
36487 |
8.4715
0.379560 minDCF
|
|
CHiME-6 Overlap
CHiME-6
|
#10/25
|
Overlap
|
39600 |
13.9722
0.658139 minDCF
|
|
ESD
ESD
|
#12/25
|
Speaking style
|
437408 |
3.0850
0.221939 minDCF
|
|
AliMeeting Near/Far
AliMeeting
|
#18/25
|
Distance
|
220000 |
9.3150
0.241885 minDCF
|
|
AliMeeting Overlap
AliMeeting
|
#11/25
|
Overlap
|
165000 |
7.4240
0.390753 minDCF
|
|
VoxKnesset
VoxKnesset
|
#9/25
|
Aging
|
158312 |
3.3600
0.138451 minDCF
|
|
VoxPopuli Aging
VoxPopuli
|
#7/25
|
Aging
|
146575 |
1.5460
0.037846 minDCF
|