{"id":"W2801612492","doi":"10.1007/s11760-018-1288-7","title":"Sound event detection in real-life audio using joint spectral and temporal features","year":2018,"lang":"en","type":"article","venue":"Signal Image and Video Processing","topic":"Music and Audio Processing","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Joint (building); Event (particle physics); Speech recognition; Deconvolution; Pattern recognition (psychology); Audio signal; Representation (politics); Word error rate; Artificial intelligence; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005532748,0.0002016467,0.0002358174,0.0001831367,0.0004879918,0.0008288172,0.0001524091,0.00008006491,0.000008429546],"category_scores_gemma":[0.00005412828,0.0001800242,0.00003220045,0.0003744269,0.0002256404,0.001587764,0.0001679256,0.0002145142,0.000002142751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005265009,"about_ca_system_score_gemma":0.0001609488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002210001,"about_ca_topic_score_gemma":0.0001222161,"domain_scores_codex":[0.9985116,0.0000680629,0.0003035202,0.0005211424,0.0002169781,0.0003787078],"domain_scores_gemma":[0.9994209,0.00002903408,0.0001746764,0.0001345096,0.0001000665,0.0001408051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008481277,0.00009358337,0.007330514,0.000542083,0.00002090522,0.0001057618,0.007704054,0.00002474063,0.4674829,0.0003204269,0.0001666602,0.5161236],"study_design_scores_gemma":[0.002565208,0.0006291769,0.0889742,0.001820536,0.00007661102,0.0009076335,0.001236584,0.4577878,0.3962701,0.04770008,0.0002530877,0.001778931],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4848753,0.0007243518,0.5135761,0.0002087997,0.00006606246,0.00007734463,3.514337e-7,0.00006328399,0.0004083691],"genre_scores_gemma":[0.971081,0.00002066501,0.02799741,0.0004818369,0.0003604456,0.000003720139,4.505925e-7,0.00001409619,0.00004034455],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5143446,"threshold_uncertainty_score":0.7992303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02965330533371822,"score_gpt":0.2901484633088295,"score_spread":0.2604951579751112,"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."}}