{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/starss23-an-audio-visual-dataset-of-spatial","title":"STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events","arxiv_id":"2306.09126","date":"2023-06-15","proceeding":"NeurIPS 2023 11","authors":["Kazuki Shimada","Archontis Politis","Parthasaarathy Sudarsanam","Daniel Krause","Kengo Uchida","Sharath Adavanne","Aapo Hakala","Yuichiro Koyama","Naoya Takahashi","Shusuke Takahashi","Tuomas Virtanen","Yuki Mitsufuji"],"abstract":"While direction of arrival (DOA) of sound events is generally estimated from multichannel audio data recorded in a microphone array, sound events usually derive from visually perceptible source objects, e.g., sounds of footsteps come from the feet of a walker. This paper proposes an audio-visual sound event localization and detection (SELD) task, which uses multichannel audio and video information to estimate the temporal activation and DOA of target sound events. Audio-visual SELD systems can detect and localize sound events using signals from a microphone array and audio-visual correspondence. We also introduce an audio-visual dataset, Sony-TAu Realistic Spatial Soundscapes 2023 (STARSS23), which consists of multichannel audio data recorded with a microphone array, video data, and spatiotemporal annotation of sound events. Sound scenes in STARSS23 are recorded with instructions, which guide recording participants to ensure adequate activity and occurrences of sound events. STARSS23 also serves human-annotated temporal activation labels and human-confirmed DOA labels, which are based on tracking results of a motion capture system. Our benchmark results demonstrate the benefits of using visual object positions in audio-visual SELD tasks. The data is available at https://zenodo.org/record/7880637.","url_abs":"https://arxiv.org/abs/2306.09126v2","url_pdf":"https://arxiv.org/pdf/2306.09126v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"starss23-an-audio-visual-dataset-of-spatial","repo_url":"https://github.com/sony/audio-visual-seld-dcase2023","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"sound-event-localization-and-detection","task_name":"Sound Event Localization and Detection"}],"methods":[],"datasets_introduced":[{"slug":"starss23","name":"STARSS23","full_name":"STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.09126","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09126"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sony/audio-visual-seld-dcase2023","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":2,"ran_honours":1,"ran":1,"ran_fixture":1,"unverified":6},"by_repo_kind":{"official":{"samples":11,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a22f198ba4f155b1","entry":"distance_between_cartesian_coordinates","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"dcase2022_task3_seld_metrics/SELD_evaluation_metrics.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/dcase2022_task3_seld_metrics/SELD_evaluation_metrics.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a22f198ba4f155b1"}},{"code_sha256_prefix":"edae90ddd4e4ad49","entry":"distance_between_spherical_coordinates_rad","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"dcase2022_task3_seld_metrics/SELD_evaluation_metrics.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/dcase2022_task3_seld_metrics/SELD_evaluation_metrics.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"edae90ddd4e4ad49"}},{"code_sha256_prefix":"3a4904de7a0d7305","entry":"least_distance_between_gt_pred","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"dcase2022_task3_seld_metrics/SELD_evaluation_metrics.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/dcase2022_task3_seld_metrics/SELD_evaluation_metrics.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a4904de7a0d7305"}},{"code_sha256_prefix":"e4ec083d3e00b43f","entry":"nCr","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"dcase2022_task3_seld_metrics/cls_feature_class.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/dcase2022_task3_seld_metrics/cls_feature_class.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4ec083d3e00b43f"}},{"code_sha256_prefix":"57e1cbd986847dd6","entry":"reshape_3Dto2D","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"dcase2022_task3_seld_metrics/cls_compute_seld_results.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/dcase2022_task3_seld_metrics/cls_compute_seld_results.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"57e1cbd986847dd6"}},{"code_sha256_prefix":"ef8e5cd28b4871ba","entry":"add_label_each_frame","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"util/func_seld_data_loader.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/util/func_seld_data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef8e5cd28b4871ba"}},{"code_sha256_prefix":"af3dcaf8eb6f2a69","entry":"get_label","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"util/func_seld_data_loader.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/util/func_seld_data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"af3dcaf8eb6f2a69"}},{"code_sha256_prefix":"6f9b312e4a5c8fd5","entry":"get_params","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"dcase2022_task3_seld_metrics/parameters.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/dcase2022_task3_seld_metrics/parameters.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f9b312e4a5c8fd5"}},{"code_sha256_prefix":"7cede3fc12270c08","entry":"jackknife_estimation","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"dcase2022_task3_seld_metrics/cls_compute_seld_results.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/dcase2022_task3_seld_metrics/cls_compute_seld_results.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7cede3fc12270c08"}},{"code_sha256_prefix":"a189efd80d1da8bb","entry":"select_time","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"util/func_seld_data_loader.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/util/func_seld_data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a189efd80d1da8bb"}},{"code_sha256_prefix":"31957915cf1bc47f","entry":"wav_path2video_frame","repo":"sony/audio-visual-seld-dcase2023","repo_kind":"official","path":"seld_data_loader.py","file_url":"https://github.com/sony/audio-visual-seld-dcase2023/blob/HEAD/seld_data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31957915cf1bc47f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}