{"url":"/dataset/starss22","name":"STARSS22","full_name":"Sony-TAu Realistic Spatial Soundscapes 2022","description_markdown":"The Sony-TAu Realistic Spatial Soundscapes 2022(STARSS22) dataset consists of recordings of real scenes captured with high channel-count spherical microphone array (SMA). The recordings are conducted from two different teams at two different sites, Tampere University in Tammere, Finland, and Sony facilities in Tokyo, Japan. Recordings at both sites share the same capturing and annotation process, and a similar organization. They are organized in sessions, corresponding to distinct rooms, human participants, and sound making props with a few exceptions.\r\n\r\nSource: [STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events](https://arxiv.org/pdf/2206.01948v2.pdf)\r\n\r\nImage [https://arxiv.org/pdf/2206.01948v2.pdf](https://arxiv.org/pdf/2206.01948v2.pdf)","description_withheld":null,"homepage":"https://zenodo.org/record/6387880#.Y1eqqezMJhE","introduced_date":"2022-06-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/starss22-a-dataset-of-spatial-recordings-of","title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","first_author":"Archontis Politis","url":null},"license":{"name":"MIT license","url":"https://opensource.org/licenses/MIT"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Sound Event Localization and Detection","url":"/task/sound-event-localization-and-detection","datasets_with_task":"/datasets/task/sound-event-localization-and-detection"}],"languages":[],"variants":["STARSS22"],"data_loaders":[],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sound-event-localization-and-detection-on-1","task":"Sound Event Localization and Detection","dataset_variant":"STARSS22","rows":2,"metrics":["Class-dependent localization error","Class-dependent localization recall","location-dependent F1-score (macro)","location-dependent F1-score (micro)","Localization-dependent error rate (20°)"],"first_row_in_archive_order":{"model":"Baseline (FOA)","paper":"/paper/starss22-a-dataset-of-spatial-recordings-of","metrics":{"Class-dependent localization error":"29.3","Class-dependent localization recall":"46","Localization-dependent error rate (20°)":"71","location-dependent F1-score (macro)":"21","location-dependent F1-score (micro)":"0.36"},"code_links":[{"title":"sharathadavanne/seld-dcase2022","url":"https://github.com/sharathadavanne/seld-dcase2022"},{"title":"prerak23/dir_srcmic_doa","url":"https://github.com/prerak23/dir_srcmic_doa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/starss22-a-dataset-of-spatial-recordings-of","title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","date":"2022-06-04","rows_on_this_dataset":2,"code_links":2,"syntology":null}],"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."}