{"url":"/dataset/tut-acoustic-scenes-2017","name":"TUT Acoustic Scenes 2017","full_name":"TUT Acoustic Scenes 2017","description_markdown":"The **TUT Acoustic Scenes 2017** dataset is a collection of recordings from various acoustic scenes all from distinct locations. For each recording location 3-5 minute long audio recordings are captured and are split into 10 seconds which act as unit of sample for this task. All the audio clips are recorded with 44.1 kHz sampling rate and 24 bit resolution.\n\nSource: [Ensemble of deep neural networks for acoustic scene classification](https://arxiv.org/abs/1708.05826)\nImage Source: [https://www.mathworks.com/help/audio/ug/acoustic-scene-recognition-using-late-fusion.html;jsessionid=95c969bc690c06fe42a7ed17f57e](https://www.mathworks.com/help/audio/ug/acoustic-scene-recognition-using-late-fusion.html;jsessionid=95c969bc690c06fe42a7ed17f57e)","description_withheld":null,"homepage":"https://zenodo.org/record/400515","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"TUT database for acoustic scene classification and sound event detection","first_author":null,"url":"https://doi.org/10.1109/EUSIPCO.2016.7760424"},"license":{"name":"Other (Non-Commercial)","url":"https://zenodo.org/record/400515"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Acoustic Scene Classification","url":"/task/acoustic-scene-classification","datasets_with_task":"/datasets/task/acoustic-scene-classification"},{"name":"Scene Classification","url":"/task/scene-classification","datasets_with_task":"/datasets/task/scene-classification"}],"languages":[],"variants":["TUT Acoustic Scenes 2017"],"data_loaders":[],"num_papers_in_archive":13,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/acoustic-scene-classification-on-tut-acoustic","task":"Acoustic Scene Classification","dataset_variant":"TUT Acoustic Scenes 2017","rows":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Qwen-Audio","paper":"/paper/qwen-audio-advancing-universal-audio","metrics":{"1:1 Accuracy":"0.649"},"code_links":[{"title":"alibaba-damo-academy/FunASR","url":"https://github.com/alibaba-damo-academy/FunASR"},{"title":"qwenlm/qwen-audio","url":"https://github.com/qwenlm/qwen-audio"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/qwen-audio-advancing-universal-audio","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","date":"2023-11-14","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":1,"samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":7,"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."}