{"url":"/dataset/cochlscene","name":"CochlScene","full_name":null,"description_markdown":"**CochlScene** is a dataset for acoustic scene classification. The dataset consists of 76k samples collected from 831 participants in 13 acoustic scenes.\r\n\r\nSource: [CochlScene: Acquisition of acoustic scene data using crowdsourcing](https://arxiv.org/pdf/2211.02289v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2211.02289v1.pdf](https://arxiv.org/pdf/2211.02289v1.pdf)","description_withheld":null,"homepage":"https://github.com/cochlearai/cochlscene","introduced_date":"2022-11-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/cochlscene-acquisition-of-acoustic-scene-data","title":"CochlScene: Acquisition of acoustic scene data using crowdsourcing","first_author":"Il-Young Jeong","url":null},"license":null,"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":["CochlScene"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/acoustic-scene-classification-on-cochlscene","task":"Acoustic Scene Classification","dataset_variant":"CochlScene","rows":2,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Audio Flamingo","paper":"/paper/audio-flamingo-a-novel-audio-language-model","metrics":{"1:1 Accuracy":"0.830"},"code_links":[{"title":"NVIDIA/audio-flamingo","url":"https://github.com/NVIDIA/audio-flamingo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/audio-flamingo-a-novel-audio-language-model","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","date":"2024-02-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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":"2026-09-24T18:15:14+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":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":10,"samples_ran":8,"samples_unverified":2,"pointer_only_for_licence":10,"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."}