Benchmark Almanac

DESED

CNN 42.7 tops its leaderboard
Not in model cards

Models identify when sound events occur in domestic environments. Meta compares frame-level predictions across audio encoders.

Made by
DESED project
Kind
Audio understanding and voice
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Audio → Time series
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Audio and speech
11
Entries on its own leaderboard, 0 models we track

CNN tops the leaderboard with 42.7

Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 1 CNN Lin_ICT_task4_3 42.7
  2. 2 CRNN Delphin_OL_task4_2 42.1
  3. 3 CRNN, Ensemble Lim_ETRI_task4_4 34.4
  4. 4 ResNet, SENet Kiyokawa_NEC_task4_4 32.4
  5. 5 NMF, CNN CTK_NU_task4_1 31.0
  6. 6 CNN,ResNet,RNN ZYL_UESTC_task4_2 30.8
  7. 7 CRNN, RBM, CRBM, PCA Kothinti_JHU_task4_1 30.7
  8. 8 CRNN, RBM, CRBM, PCA, Kalman Filter Kothinti_JHU_task4_4 29.4
  9. 9 CNN, RNN, ensemble bolun_NWPU_task4_2 27.8
  10. 10 ResNet Mishima_NEC_task4_4 19.8
  11. 11 CMRANN-MT Wang_YSU_task4_3 6.70

Source: Official DESED leaderboard

#EntryScoreSettingSubmitted byDateSource
1 CNN 42.7 Lin_ICT_task4_3 Guiding_learning_3 Official leaderboard
2 CRNN 42.1 Delphin_OL_task4_2 DCASE2019 mean-teacher with shifted and noisy data augmentation system Official leaderboard
3 CRNN, Ensemble 34.4 Lim_ETRI_task4_4 Lim_task4_4 Official leaderboard
4 ResNet, SENet 32.4 Kiyokawa_NEC_task4_4 DCASE2019 SED ResNet self-mask kiyo Official leaderboard
5 NMF, CNN 31.0 CTK_NU_task4_1 CTK_NU_task4_1 Official leaderboard
6 CNN,ResNet,RNN 30.8 ZYL_UESTC_task4_2 UESTC_SICE_task4_2 Official leaderboard
7 CRNN, RBM, CRBM, PCA 30.7 Kothinti_JHU_task4_1 JHU DCASE2019 task4 system Official leaderboard
8 CRNN, RBM, CRBM, PCA, Kalman Filter 29.4 Kothinti_JHU_task4_4 JHU DCASE2019 task4 system Official leaderboard
9 CNN, RNN, ensemble 27.8 bolun_NWPU_task4_2 DCASE2019 task4 system Official leaderboard
10 ResNet 19.8 Mishima_NEC_task4_4 msm_ResNet_4_augmentation_pseudo Official leaderboard
11 CMRANN-MT 6.70 Wang_YSU_task4_3 Wang_YSU_task4_3 Official leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Audio and video

All 695 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 11 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on project.inria.fr: 11 entries at the last read, none a model we track.
  • Pass Last read November 21st, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check