{"id":"W4372260217","doi":"10.1109/icassp49357.2023.10096198","title":"Epic-Sounds: A Large-Scale Dataset of Actions that Sound","year":2023,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geomechanica (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"EPIC; Computer science; Sound (geography); Annotation; Pipeline (software); Class (philosophy); Audio visual; Visualization; Code (set theory); Scale (ratio); Object (grammar); Speech recognition; Artificial intelligence; Multimedia; Acoustics; Cartography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005869695,0.002845853,0.00102452,0.003222135,0.0008486653,0.001230254,0.001849148,0.00209686,0.009850102],"category_scores_gemma":[0.003351867,0.0004504657,0.001225771,0.002618579,0.0007164648,0.001658317,0.002303792,0.001428017,0.01506697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000860434,"about_ca_system_score_gemma":0.001114288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01524701,"about_ca_topic_score_gemma":0.05847336,"domain_scores_codex":[0.9986475,0.0001725524,0.0001312934,0.0004930684,0.0003812045,0.0001744296],"domain_scores_gemma":[0.998609,0.000315105,0.0001355469,0.0003791877,0.0003524502,0.0002086506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002069823,0.0005933897,0.01889436,0.004542594,0.0003624152,0.001312873,0.001322267,0.004598241,0.0226591,0.0014658,0.7477904,0.1943888],"study_design_scores_gemma":[0.0004107664,0.0006748259,0.1654857,0.001159229,0.0003132058,0.002546533,0.003008224,0.02568781,0.01638247,0.004211649,0.7796949,0.0004246963],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.05475333,0.003349694,0.0162088,0.0004849003,0.001060084,0.0006336357,0.8830852,0.02639902,0.01402541],"genre_scores_gemma":[0.03442066,0.0005383298,0.01948306,0.0002123809,0.0001324062,0.0005165428,0.9395935,0.0006575155,0.004445624],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01524701,"threshold_uncertainty_score":0.03295189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0783861517944466,"score_gpt":0.3177064082020132,"score_spread":0.2393202564075666,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}