Datasets › AudioSet
AudioSet
Audioset is an audio event dataset, which consists of over 2M human-annotated 10-second video clips. These clips are collected from YouTube, therefore many of which are in poor-quality and contain multiple sound-sources. A hierarchical ontology of 632 event classes is employed to annotate these data, which means that the same sound could be annotated as different labels. For example, the sound of barking is annotated as Animal, Pets, and Dog. All the videos are split into Evaluation/Balanced-Train/Unbalanced-Train set.
Source: Curriculum Audiovisual Learning
Benchmarks archive 2025-07-28
All 5 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Audio Classification | AudioSet | OmniVec2 Test mAP 0.558 | OmniVec2 - A Novel Transformer based Network for Large... | — | 51 | Compare |
| Audio Tagging | AudioSet | CAV-MAE (Audio-Visual) mean average precision 0.512 | Contrastive Audio-Visual Masked Autoencoder | yuangongnd/cav-mae | 11 | Compare |
| Audio Source Separation | AudioSet | ST-SED-SEP SDR 10.55 | Zero-shot Audio Source Separation through Query-based... | RetroCirce/Zero_Shot_Audio_Source_Separation | 2 | Compare |
| Multi-modal Classification | AudioSet | CAV-MAE Average mAP 0.512 | Contrastive Audio-Visual Masked Autoencoder | yuangongnd/cav-mae | 2 | Compare |
| Target Sound Extraction | AudioSet | CLAPSep SDRi 9.29 | CLAPSep: Leveraging Contrastive Pre-trained Model for... | aisaka0v0/clapsep | 1 | Compare |
Papers archive 2025-07-28
30 shown of 38 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 744. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
The full list of 38 is in the JSON twin.
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- AudioSet
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections