Speaker Verification Benchmark

OpenSVBench Leaderboard

Cross-scenario evaluation of speaker verification systems on a fixed public core. The global ranking uses source-balanced scenario-macro EER; lower is better.

18 ranked systems 11 scenarios 26 trial sets 16 source datasets

Submit a system Browse scenarios

Fixed-Core Ranking

Global ranking

Only reviewed, completed submissions with full current-core coverage are included.

Current leader: wespeaker/w2vbert2

Rank	System	EER ↓ Scenario macro	minDCF ↓ Scenario macro	Stronger Scenarios	Weaker Scenarios
#1	wespeaker/w2vbert2 vb2-w2vbert	9.9604	0.360767	Noise/reverb Speaking style	Genre shift Channel/device
#2	palabraai/redimnet2-b6 redimnet2	10.5277	0.419432	Overlap Aging	Genre shift In-the-wild
#3	wespeaker/samresnet100 vb2-sam100	10.5780	0.390239	Aging Noise/reverb	Accent/dialect Channel/device
#4	wespeaker/res152-voxceleb wespeaker_resnet152	11.2275	0.442748	Speaking style In-the-wild	Genre shift Channel/device
#5	wespeaker/res293-voxceleb wespeaker_resnet293	11.3130	0.439607	Cross-lingual Aging	Genre shift In-the-wild
#6	iic/eres2netv2-zh eresv2_zh	11.5449	0.484961	Genre shift Channel/device	Noise/reverb Overlap
#7	wespeaker/res34-voxceleb wespeaker_resnet34_voxceleb	12.0516	0.477054	Aging Speaking style	Channel/device Short-duration
#8	iic/eres2net-en eres_en	12.0955	0.472802	Noise/reverb Overlap	Genre shift Short-duration
#9	wespeaker/campplus-voxceleb campplus_wespeaker	13.4165	0.520675	Aging Overlap	Genre shift Channel/device
#10	speechbrain/ecapa ecapa	13.5461	0.543660	Noise/reverb Accent/dialect	Cross-lingual Short-duration
#11	wespeaker/ecapa1024-voxceleb wespeaker_ecapa1024	14.0835	0.534111	Aging Speaking style	Genre shift Short-duration
#12	iic/eres2net-large-3dspeaker eres2net_large_3dspeaker	14.1682	0.593516	Channel/device Distance	Aging In-the-wild
#13	wespeaker/ecapa512-voxceleb wespeaker_ecapa512	14.3120	0.541141	Aging Cross-lingual	Genre shift Channel/device
#14	wespeaker/res34-cnceleb wespeaker_r34	14.4910	0.607964	Genre shift Short-duration	Channel/device Distance
#15	iic/campplus campplus	15.1677	0.590178	Genre shift Channel/device	Noise/reverb Accent/dialect
#16	speechbrain/xvector xvector	23.3539	0.776078	Aging Noise/reverb	Accent/dialect In-the-wild
#17	microsoft/wavlm-base-plus-sv wavlm_base	25.1577	0.875090	Aging In-the-wild	Genre shift Distance
#18	microsoft/unispeech-sat-base-plus-sv unispeech_sat_base_plus	25.6711	0.890736	Noise/reverb Short-duration	Channel/device Overlap

Diagnostic Views

Scenario overview

Use scenario rankings to inspect deployment-specific strengths and failure modes hidden by the aggregate score.

Open full scenario index

Scenario	Evaluation Focus	Trial Sets	Current Leader
Accent / Dialect Robustness Accent/dialect	Accent and dialect variation	2	wespeaker/w2vbert2
Aging Robustness Aging	Speaker aging and time gaps	2	wespeaker/samresnet100
Channel / Device Robustness Channel/device	Device and channel variation	2	iic/eres2net-large-3dspeaker
Cross-Lingual Robustness Cross-lingual	Language mismatch	1	wespeaker/w2vbert2
Distance Robustness Distance	Distance mismatch	4	iic/eres2net-large-3dspeaker
Genre-Shift Robustness Genre shift	Source-genre variation	1	iic/eres2netv2-zh
In-The-Wild Robustness In-the-wild	Open-domain media speech	4	wespeaker/w2vbert2
Noise / Reverb Robustness Noise/reverb	Noise and reverberation	1	wespeaker/w2vbert2
Overlap Robustness Overlap	Overlapping speakers	2	wespeaker/w2vbert2
Short-Duration Robustness Short-duration	Short-duration speech	4	wespeaker/w2vbert2
Speaking-Style Robustness Speaking style	Speaking style shift	3	wespeaker/w2vbert2