{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003688222,0.0004160324,0.000355522,0.001239716,0.0001942645,0.0005456598,0.0002923495,0.0005594463,0.001364413],"category_scores_gemma":[0.0009845514,0.0001398053,0.0003618723,0.0007258885,0.0002419023,0.0007481117,0.0004062244,0.0003270438,0.0007113866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001038035,"about_ca_system_score_gemma":0.0002521283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006631422,"about_ca_topic_score_gemma":0.001361619,"domain_scores_codex":[0.9998026,0.00002367769,0.00001275254,0.00005312433,0.00007046735,0.00003739946],"domain_scores_gemma":[0.9996431,0.0001427534,0.00004835497,0.0000312705,0.00008719813,0.00004732077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00164194,0.0003136877,0.01497686,0.00023798,0.0001261799,0.0006426219,0.0001279913,0.009415885,0.4465089,0.00131724,0.001407206,0.5232835],"study_design_scores_gemma":[0.00008921104,0.0006370498,0.09697922,0.00006043071,0.0002589062,0.002427909,0.0003327263,0.7149023,0.1764832,0.003236895,0.004517104,0.00007511978],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3842718,0.0009206755,0.6101621,0.0001629115,0.0001585008,0.00006521301,0.0004432527,0.001119424,0.002696127],"genre_scores_gemma":[0.8904016,0.0005451065,0.1065958,0.00005318737,0.0001121918,0.00002814713,0.0004511429,0.00006085987,0.001751986],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001364413,"threshold_uncertainty_score":0.004564404,"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."}}