{"id":"W2906473190","doi":"10.32920/ryerson.14653065.v1","title":"Temporal patterns and ensemble learning for environmental sound recognition","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mel-frequency cepstrum; Pattern recognition (psychology); Computer science; Artificial intelligence; Classifier (UML); Deconvolution; Local binary patterns; Speech recognition; Binary number; Word error rate; Ensemble learning; Feature extraction; Mathematics; Histogram; Algorithm","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":[0.0001621618,0.0001492522,0.0001670559,0.00004031691,0.0001536607,0.0005663448,0.0001873074,0.0001201518,0.00006178186],"category_scores_gemma":[0.00001249806,0.0001485307,0.00006264681,0.00002198939,0.0000195085,0.0002266432,0.0008015695,0.0002520389,0.000005799039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002811739,"about_ca_system_score_gemma":0.00004100988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002246176,"about_ca_topic_score_gemma":0.0000148874,"domain_scores_codex":[0.9989661,0.00003395679,0.0001622939,0.00054224,0.0001253221,0.0001700741],"domain_scores_gemma":[0.9995838,0.00004738769,0.0001212992,0.0001790598,0.00001475895,0.00005371662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005558058,0.00007488915,0.01644907,0.0005505313,0.00005245742,0.00002057632,0.002020297,0.0001637508,0.001332973,0.00008815213,0.0004002239,0.9788415],"study_design_scores_gemma":[0.004849661,0.0007651698,0.04367385,0.003322797,0.0002972521,0.000457969,0.006375885,0.7273657,0.06631816,0.1211361,0.0186695,0.006768058],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2684769,0.0001434153,0.7300742,0.000210653,0.0001988105,0.0001191393,0.00000334436,0.00006048898,0.0007129999],"genre_scores_gemma":[0.9200669,0.0000537697,0.07819494,0.0004033908,0.0001176441,0.00003287255,0.0001534936,0.00001103563,0.0009659401],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9720734,"threshold_uncertainty_score":0.6056905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03887353396488515,"score_gpt":0.2479602679144031,"score_spread":0.2090867339495179,"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."}}