{"id":"W3191309868","doi":"10.1109/jiot.2021.3098464","title":"Environmental Sound Classification via Time–Frequency Attention and Framewise Self-Attention-Based Deep Neural Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Music and Audio Processing","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Clutter; Spectrogram; Normalization (sociology); Artificial intelligence; Relevance (law); Speech recognition; Artificial neural network; Set (abstract data type); Time–frequency analysis; Data set; Pattern recognition (psychology); Machine learning; Radar; Telecommunications","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":[0.0003444881,0.0001459785,0.0001736307,0.00008728525,0.0001457473,0.0004236722,0.0003837837,0.00009977869,0.00008017679],"category_scores_gemma":[0.00001711716,0.0001403873,0.0001183589,0.0001132226,0.00007026907,0.001043921,0.00007294889,0.000406893,0.00001176113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007875254,"about_ca_system_score_gemma":0.00003291375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004082759,"about_ca_topic_score_gemma":6.294337e-7,"domain_scores_codex":[0.9986272,0.0001067943,0.0004278732,0.0002895077,0.0003313726,0.0002171806],"domain_scores_gemma":[0.9990774,0.00005678527,0.0004782761,0.0001939424,0.00007932309,0.0001142852],"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":[0.00005537454,0.0009723156,0.07417429,0.0001688517,0.000405262,0.0003575246,0.003868564,0.003333757,0.5484983,0.0007630253,0.001556367,0.3658463],"study_design_scores_gemma":[0.0003842535,0.00006678866,0.009392966,0.00008973443,0.00003961225,0.0005231641,0.00002803438,0.9842129,0.00267234,0.002398625,0.00003057245,0.0001609849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3561669,0.0003968787,0.6422749,0.0005473983,0.0004809149,0.0000320057,3.280246e-7,0.00002901015,0.00007170693],"genre_scores_gemma":[0.9693292,0.00001922183,0.02967773,0.0007255761,0.0001553998,0.000001806756,0.000004697904,0.00001113499,0.00007518358],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9808792,"threshold_uncertainty_score":0.5724829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009778943174724202,"score_gpt":0.2180775048520583,"score_spread":0.2082985616773341,"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."}}