Benchmark Scenario

Short-Duration Robustness

How much performance holds up when speech evidence is limited by duration.

Short-duration Short-duration speech 4 trial sets

Back To Scenario Index Open Global Leaderboard

Current Leader

wespeaker/w2vbert2

18 ranked

12.5144

scenario EER

0.441680 scenario minDCF

Scenario Coverage

4 trial sets

HI-MIA GSC Short CN-Celeb Short VoxCeleb Short

Scenario Leaders

Top systems on this scenario

The current reviewed submissions for this scenario.

wespeaker/w2vbert2

vb2-w2vbert

12.5144

scenario EER

0.441680 scenario minDCF

iic/eres2netv2-zh

eresv2_zh

12.9695

scenario EER

0.460887 scenario minDCF

palabraai/redimnet2-b6

redimnet2

13.2481

scenario EER

0.531421 scenario minDCF

Scenario Ranking

Full ranking for Short-Duration Robustness

A scenario row first averages linked trial sets within each source dataset, then averages the source means and ranks systems by the resulting EER.

This Scenario All Scenarios Global Board

Rank	System	Rank Signal	Scenario EER	Scenario minDCF	Evidence Rank / EER by trial-set order: HI-MIA · GSC Short · CN-Celeb Short · VoxCeleb Short
#1	wespeaker/w2vbert2 vb2-w2vbert	Leader	12.5144	0.441680	#8 7.0400 #2 6.0250 #8 25.9130 #2 11.0796
#2	iic/eres2netv2-zh eresv2_zh	Top 3	12.9695	0.460887	#2 3.7090 #1 5.0750 #2 17.6675 #15 25.4264
#3	palabraai/redimnet2-b6 redimnet2	Top 3	13.2481	0.531421	#3 5.7113 #8 12.3950 #4 24.2213 #1 10.6649
#4	wespeaker/samresnet100 vb2-sam100	Competitive	13.4479	0.497755	#6 5.9033 #6 11.2450 #6 25.4042 #3 11.2390
#5	wespeaker/res152-voxceleb wespeaker_resnet152	Competitive	13.5058	0.545781	#4 5.8453 #5 10.8860 #5 24.9437 #4 12.3481
#6	wespeaker/res293-voxceleb wespeaker_resnet293	Competitive	14.0805	0.568931	#7 6.3817 #7 11.4500 #9 26.0196 #5 12.4707
#7	wespeaker/res34-cnceleb wespeaker_r34	Competitive	14.2898	0.579413	#12 7.7542 #4 8.3650 #1 17.6675 #14 23.3725
#8	iic/campplus campplus	Competitive	14.8056	0.554588	#5 5.8722 #3 7.0055 #3 19.1292 #16 27.2155
#9	wespeaker/res34-voxceleb wespeaker_resnet34_voxceleb	Competitive	14.9080	0.610039	#9 7.0523 #10 13.2190 #7 25.4223 #7 13.9382
#10	iic/eres2net-en eres_en	Needs work	15.8159	0.582696	#10 7.0967 #12 13.8900 #11 27.2323 #9 15.0446
#11	wespeaker/campplus-voxceleb campplus_wespeaker	Needs work	16.3494	0.638979	#13 7.9797 #13 16.4345 #12 27.4153 #6 13.5682
#12	wespeaker/ecapa512-voxceleb wespeaker_ecapa512	Needs work	16.5541	0.604686	#14 8.5340 #9 12.8770 #14 29.6374 #10 15.1680
#13	speechbrain/ecapa ecapa	Needs work	17.0764	0.621298	#11 7.6850 #14 17.0600 #13 28.7238 #8 14.8367
#14	iic/eres2net-large-3dspeaker eres2net_large_3dspeaker	Needs work	17.5708	0.654520	#1 2.8963 #11 13.3500 #10 26.8023 #17 27.2344
#15	wespeaker/ecapa1024-voxceleb wespeaker_ecapa1024	Needs work	18.2450	0.644928	#15 8.6250 #15 17.4110 #15 30.3869 #11 16.5570
#16	speechbrain/xvector xvector	Needs work	25.0788	0.830830	#16 12.0075 #16 17.5650 #18 37.8590 #18 32.8837
#17	microsoft/unispeech-sat-base-plus-sv unispeech_sat_base_plus	Needs work	26.1478	0.927872	#17 23.7600 #17 24.4600 #17 34.0117 #12 22.3595
#18	microsoft/wavlm-base-plus-sv wavlm_base	Needs work	26.7099	0.906048	#18 25.0650 #18 25.7750 #16 33.2598 #13 22.7399