{"url":"/dataset/urbansound8k-1","name":"UrbanSound8K","full_name":"UrbanSound8K","description_markdown":"Urban Sound 8K is an audio dataset that contains 8732 labeled sound excerpts (<=4s) of urban sounds from 10 classes: air_conditioner, car_horn, children_playing, dog_bark, drilling, enginge_idling, gun_shot, jackhammer, siren, and street_music. The classes are drawn from the urban sound taxonomy. All excerpts are taken from field recordings uploaded to www.freesound.org.\r\n\r\nSource: [https://zenodo.org/record/401395](https://zenodo.org/record/401395)\r\nImage Source: [https://urbansounddataset.weebly.com/urbansound8k.html](https://urbansounddataset.weebly.com/urbansound8k.html)","description_withheld":null,"homepage":"https://urbansounddataset.weebly.com/urbansound8k.html","introduced_date":"2014-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"A Dataset and Taxonomy for Urban Sound Research","first_author":null,"url":"https://dl.acm.org/doi/10.1145/2647868.2655045"},"license":{"name":"CC BY-NC 3.0","url":"https://creativecommons.org/licenses/by-nc/3.0/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Audio Classification","url":"/task/audio-classification","datasets_with_task":"/datasets/task/audio-classification"},{"name":"Data Augmentation","url":"/task/data-augmentation","datasets_with_task":"/datasets/task/data-augmentation"},{"name":"Zero-shot Audio Classification","url":"/task/zero-shot-audio-classification","datasets_with_task":"/datasets/task/zero-shot-audio-classification"},{"name":"Environmental Sound Classification","url":"/task/environmental-sound-classification","datasets_with_task":"/datasets/task/environmental-sound-classification"},{"name":"Environment Sound Classification","url":"/task/environment-sound-classification","datasets_with_task":"/datasets/task/environment-sound-classification"}],"languages":[],"variants":["UrbanSound8K"],"data_loaders":[],"num_papers_in_archive":147,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/environmental-sound-classification-on","task":"Environmental Sound Classification","dataset_variant":"UrbanSound8K","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"AudioCLIP","paper":"/paper/audioclip-extending-clip-to-image-text-and","metrics":{"Accuracy":"90.07"},"code_links":[{"title":"iver56/audiomentations","url":"https://github.com/iver56/audiomentations"},{"title":"asteroid-team/torch-audiomentations","url":"https://github.com/asteroid-team/torch-audiomentations"},{"title":"AndreyGuzhov/AudioCLIP","url":"https://github.com/AndreyGuzhov/AudioCLIP"},{"title":"julirao/whisper_audio_classification","url":"https://github.com/julirao/whisper_audio_classification"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/masked-latent-prediction-and-classification","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","date":"2025-02-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/audioclip-extending-clip-to-image-text-and","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","date":"2021-06-24","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/end-to-end-environmental-sound-classification","title":"End-to-End Environmental Sound Classification using a 1D Convolutional Neural Network","date":"2019-04-18","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}