{"id":"W2133401807","doi":"10.1109/icassp.2004.1327198","title":"Content based audio classification and retrieval using joint time-frequency analysis","year":2004,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Centroid; Computer science; Music information retrieval; Pattern recognition (psychology); Linear discriminant analysis; Audio signal processing; Audio signal; Artificial intelligence; Speech recognition; Time–frequency analysis; Speech coding; Computer vision","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":[0.0002744574,0.00009589555,0.0001690007,0.000176384,0.0001495495,0.0001947387,0.0001825181,0.00004377836,0.00003571354],"category_scores_gemma":[0.00004483491,0.00007949146,0.00006865078,0.0008484462,0.0000482541,0.0003627107,0.00005179462,0.00006220664,0.00001747473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009008901,"about_ca_system_score_gemma":0.0001363387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007358505,"about_ca_topic_score_gemma":0.000003881186,"domain_scores_codex":[0.9990498,0.00002697045,0.0002165704,0.0003318685,0.0002112338,0.0001635816],"domain_scores_gemma":[0.9993817,0.00002001192,0.0001141446,0.0003000316,0.0001027048,0.00008145302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001441658,0.0001779466,0.007009945,0.00005785215,0.0002707785,0.00002654785,0.0006839793,0.004577815,0.9338778,0.04083783,0.00009742549,0.01236763],"study_design_scores_gemma":[0.0008996968,0.00006114187,0.03771483,0.00005290464,0.0001991859,0.00001229677,0.00004950586,0.8776056,0.07831171,0.004662092,0.00005214356,0.0003789031],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1897389,0.00006010569,0.8071399,0.002020637,0.00003530149,0.00005532865,4.731427e-7,0.0001294595,0.0008198962],"genre_scores_gemma":[0.7683298,0.000001934461,0.2306826,0.0008605078,0.00002104261,4.367952e-7,0.000001316934,0.000004381864,0.0000979971],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8730277,"threshold_uncertainty_score":0.3241568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09747529054424402,"score_gpt":0.2620883164863804,"score_spread":0.1646130259421364,"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."}}