{"url":"/dataset/desed","name":"DESED","full_name":"Domestic environment sound event detection","description_markdown":"The **DESED** dataset is a dataset designed to recognize sound event classes in domestic environments. The dataset is designed to be used for sound event detection (SED, recognize events with their time boundaries) but it can also be used for sound event tagging (SET, indicate presence of an event in an audio file).\r\nThe dataset is composed of 10 event classes to recognize in 10 second audio files. The classes are: Alarm/bell/ringing, Blender, Cat, Dog, Dishes,\r\nElectric shaver/toothbrush, Frying, Running water, Speech, Vacuum cleaner.\r\n\r\nSource: [https://project.inria.fr/desed/](https://project.inria.fr/desed/)\r\nImage Source: [https://project.inria.fr/desed/](https://project.inria.fr/desed/)","description_withheld":null,"homepage":"https://project.inria.fr/desed/","introduced_date":"2019-10-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/sound-event-detection-in-domestic","title":"Sound event detection in domestic environments withweakly labeled data and soundscape synthesis","first_author":"Nicolas Turpault","url":null},"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Sound Event Detection","url":"/task/sound-event-detection","datasets_with_task":"/datasets/task/sound-event-detection"}],"languages":[],"variants":["DESED"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sound-event-detection-on-desed","task":"Sound Event Detection","dataset_variant":"DESED","rows":13,"metrics":["event-based F1 score","PSDS1","PSDS2"],"first_row_in_archive_order":{"model":"ATST-SED","paper":"/paper/fine-tune-the-pretrained-atst-model-for-sound","metrics":{"PSDS1":"0.583","PSDS2":"0.810","event-based F1 score":"63.4"},"code_links":[{"title":"Audio-WestlakeU/ATST-SED","url":"https://github.com/Audio-WestlakeU/ATST-SED"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/jitter-jigsaw-temporal-transformer-for-event","title":"JiTTER: Jigsaw Temporal Transformer for Event Reconstruction for Self-Supervised Sound Event Detection","date":"2025-02-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mat-sed-amasked-audio-transformer-with-masked","title":"MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection","date":"2024-08-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pushing-the-limit-of-sound-event-detection","title":"Pushing the Limit of Sound Event Detection with Multi-Dilated Frequency Dynamic Convolution","date":"2024-06-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/dual-knowledge-distillation-for-efficient","title":"Dual Knowledge Distillation for Efficient Sound Event Detection","date":"2024-02-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fine-tune-the-pretrained-atst-model-for-sound","title":"Fine-tune the pretrained ATST model for sound event detection","date":"2023-09-15","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":10,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/frequency-dynamic-convolution-frequency","title":"Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection","date":"2022-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hts-at-a-hierarchical-token-semantic-audio","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","date":"2022-02-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":4,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rct-random-consistency-training-for-semi","title":"RCT: Random Consistency Training for Semi-supervised Sound Event Detection","date":"2021-10-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/heavily-augmented-sound-event-detection","title":"Heavily Augmented Sound Event Detection utilizing Weak Predictions","date":"2021-07-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sound-event-detection-in-domestic","title":"Sound event detection in domestic environments withweakly labeled data and soundscape synthesis","date":"2019-10-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/training-sound-event-detection-on-a-1","title":"Training Sound Event Detection On A Heterogeneous Dataset","date":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-sound-event-detection-in-domestic-1","title":"Improving Sound Event Detection In Domestic Environments Using Sound Separation","date":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":30,"samples_ran":14,"samples_unverified":16,"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."}