{"url":"/dataset/esc50","name":"ESC50","full_name":"ESC: Dataset for Environmental Sound Classification","description_markdown":"The ESC-50 dataset is a labeled collection of 2000 environmental audio recordings suitable for benchmarking methods of environmental sound classification.\r\n\r\nThe dataset consists of 5-second-long recordings organized into 50 semantical classes (with 40 examples per class) loosely arranged into 5 major categories.\r\n\r\nReference: [https://dl.acm.org/doi/10.1145/2733373.2806390](https://dl.acm.org/doi/10.1145/2733373.2806390)","description_withheld":null,"homepage":"https://github.com/karolpiczak/ESC-50","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"The dataset is available under the terms of the Creative Commons Attribution Non-Commercial license.","url":"https://creativecommons.org/licenses/by-nc/3.0/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Environmental Sound Classification","url":"/task/environmental-sound-classification","datasets_with_task":"/datasets/task/environmental-sound-classification"},{"name":"Linear evaluation","url":"/task/linear-evaluation","datasets_with_task":"/datasets/task/linear-evaluation"}],"languages":[],"variants":["ESC50"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}