{"id":"W1496168202","doi":"10.1109/icassp.2015.7178279","title":"Efficient spectrogram-based binary image feature for audio copy detection","year":2015,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal; École de Technologie Supérieure","funders":"","keywords":"Spectrogram; Feature (linguistics); Computer science; Binary number; Pattern recognition (psychology); Artificial intelligence; Image (mathematics); Feature extraction; ENCODE; Speech recognition; Computer vision; Mathematics","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":[0.0003366568,0.0005942763,0.0008281616,0.002231289,0.0002601542,0.0006298186,0.0009849342,0.0005179135,0.003369293],"category_scores_gemma":[0.001555813,0.0002368761,0.0004235085,0.001134156,0.0002470601,0.001351233,0.0005899784,0.0004883001,0.00253588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000383169,"about_ca_system_score_gemma":0.0003990617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002002059,"about_ca_topic_score_gemma":0.003307554,"domain_scores_codex":[0.999357,0.00005270576,0.00003373442,0.0001021964,0.0003985502,0.00005590167],"domain_scores_gemma":[0.9989772,0.0002706344,0.0001178941,0.0002195894,0.0003633104,0.00005134114],"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":[0.00060844,0.0001242944,0.001752647,0.0002008471,0.00004972708,0.0001325441,0.00006453741,0.002662096,0.3347132,0.0008628388,0.00512378,0.6537051],"study_design_scores_gemma":[0.0001430801,0.0007872499,0.018829,0.00004754571,0.0001869571,0.002914282,0.0001441344,0.3896998,0.5502098,0.002353241,0.03449051,0.0001944967],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1126103,0.001992287,0.8702922,0.0002021239,0.0002454815,0.0001647412,0.001099979,0.0106433,0.002749422],"genre_scores_gemma":[0.3648723,0.000801225,0.6253062,0.0001480997,0.0002786715,0.0001602355,0.00260847,0.0004423542,0.005382403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003369293,"threshold_uncertainty_score":0.01127142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01985383422869736,"score_gpt":0.2621295588702068,"score_spread":0.2422757246415095,"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."}}