FSD50K (Freesound Database 50K)

Introduced by Eduardo Fonseca et al. in FSD50K: An Open Dataset of Human-Labeled Sound Events archive 2025-07-28

Freesound Dataset 50k (or FSD50K for short) is an open dataset of human-labeled sound events containing 51,197 Freesound clips unequally distributed in 200 classes drawn from the AudioSet Ontology. FSD50K has been created at the Music Technology Group of Universitat Pompeu Fabra. It consists mainly of sound events produced by physical sound sources and production mechanisms, including human sounds, sounds of things, animals, natural sounds, musical instruments and more.

Source: https://zenodo.org/record/4060432 Image Source: https://labs.freesound.org/datasets/

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 2 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	FSD50K	ONE-PEACE mAP 69.7	ONE-PEACE: Exploring One General Representation Model...	modelscope/modelscope +1	10	Compare
Environmental Sound Classification	FSD50K	[ABT] AudioNTT mAP 0.474	Audio Barlow Twins: Self-Supervised Audio Representation Learning	jonahanton/ssl_audio	1	Compare

Papers archive 2025-07-28

9 shown of 9 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 155. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning	1	1	17 Feb 2025	not harvested
LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging	0	1	7 Jan 2025	not harvested
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models	1	2	24 Oct 2023	not harvested
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities	2	1	18 May 2023	ran 2 of 7 samples (5 unverified)
Audio Barlow Twins: Self-Supervised Audio Representation Learning	1	1	28 Sep 2022	ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Temporal Knowledge Distillation for On-device Audio Classification	0	1	27 Oct 2021	not harvested
Efficient Training of Audio Transformers with Patchout	2	2	11 Oct 2021	ran 3 of 3 samples (0 unverified)
Audio Transformers	0	1	1 May 2021	not harvested
PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation	1	1	2 Feb 2021	not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Domain Adaptation Audio Classification Contrastive Learning Environmental Sound Classification

License archive 2025-07-28

Other (Attribution)

Modalities archive 2025-07-28

Audio

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

FSD50K

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