{"id":"W1979594949","doi":"10.5430/air.v2n1p107","title":"Noise-Robust environmental sound classification method based on combination of ICA and MP features","year":2012,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Information and Communications Technology; Iran Telecommunication Research Center","keywords":"Mel-frequency cepstrum; Environmental noise; Noise (video); Computer science; Speech recognition; Feature extraction; Independent component analysis; Pattern recognition (psychology); Feature (linguistics); Artificial intelligence; Background noise; Context (archaeology); Ambient noise level; Sound (geography); Acoustics; Telecommunications","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002406087,0.00009704313,0.0001147429,0.0002762119,0.000276031,0.0001561662,0.0004140776,0.00007984269,0.00002934548],"category_scores_gemma":[0.0002655696,0.00008844485,0.00003302047,0.0004881882,0.000227492,0.0004421868,0.0001187905,0.000284081,0.00006811701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007607752,"about_ca_system_score_gemma":0.00004979132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002114407,"about_ca_topic_score_gemma":0.000004373629,"domain_scores_codex":[0.9980265,0.0003117167,0.0002349938,0.0003095045,0.0007090087,0.0004081972],"domain_scores_gemma":[0.9987156,0.0006482776,0.00007699713,0.0003389228,0.00008363727,0.0001365966],"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":[0.00005339959,0.0006224742,0.003246211,0.00003431501,0.000007529748,0.000001482414,0.001186,0.0005004897,0.1503358,0.08067293,0.0000883269,0.7632511],"study_design_scores_gemma":[0.00003318153,0.000185348,0.009678013,0.00002671542,0.000002765608,0.000003279514,0.0005759857,0.1170097,0.8355272,0.03674714,0.00009459911,0.0001160373],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1080953,0.0002399957,0.8884816,0.001451171,0.0001233515,0.0002281674,0.000002637031,0.00003421067,0.001343615],"genre_scores_gemma":[0.9560134,0.00002483071,0.04376614,0.0000581762,0.00006611687,0.00001565999,0.000004242458,0.000007518416,0.00004385184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8479182,"threshold_uncertainty_score":0.3606676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2145145657511374,"score_gpt":0.4207561876921068,"score_spread":0.2062416219409694,"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."}}