{"id":"W3160845765","doi":"10.48550/arxiv.2011.00801","title":"Sound Event Detection and Separation: a Benchmark on Desed Synthetic\\n Soundscapes","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Soundscape; Benchmark (surveying); Sound (geography); Event (particle physics); Computer science; Separation (statistics); Acoustics; Source separation; Speech recognition; Geology; Machine learning; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007699885,0.0001013273,0.00009388064,0.00005096218,0.0002286797,0.0001106545,0.0002401996,0.00004331439,0.00002577941],"category_scores_gemma":[0.00002433666,0.0001066126,0.00003904509,0.0003844916,0.00004361611,0.0004111327,0.0001045381,0.00009118851,0.00004569809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003270271,"about_ca_system_score_gemma":0.00002798523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003941798,"about_ca_topic_score_gemma":0.000007007166,"domain_scores_codex":[0.9992565,0.00004338198,0.00007544274,0.0004226759,0.00005845852,0.0001435688],"domain_scores_gemma":[0.9995592,0.00005564425,0.00006268551,0.0001713568,0.0000351085,0.0001160073],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006007315,0.0004972491,0.00946786,0.0003789468,0.0002863989,0.0007741879,0.01201212,0.1609153,0.01845229,0.694768,0.002428074,0.09941877],"study_design_scores_gemma":[0.0006236367,0.0002834443,0.001381778,0.0000342421,0.00002553914,0.00001214927,0.0001763645,0.9677385,0.003609414,0.02317163,0.002608647,0.0003346386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3829065,0.00001939266,0.6145351,0.000396489,0.00005398822,0.00005108459,3.667302e-7,0.0000728611,0.001964176],"genre_scores_gemma":[0.9986795,0.00001033494,0.000380355,0.0007367482,0.00005037725,2.811139e-7,4.3722e-7,0.00000426639,0.0001376753],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8068232,"threshold_uncertainty_score":0.4347537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05467324964209232,"score_gpt":0.1896939428855383,"score_spread":0.1350206932434459,"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."}}