{"id":"W2976594877","doi":"10.1016/j.apacoust.2019.107020","title":"Trends in audio signal feature extraction methods","year":2019,"lang":"en","type":"article","venue":"Applied Acoustics","topic":"Music and Audio Processing","field":"Computer Science","cited_by":467,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; Ryerson University","keywords":"Computer science; Feature extraction; SIGNAL (programming language); Audio signal; Speech recognition; Signal processing; Audio signal processing; Frequency domain; Wavelet; Mel-frequency cepstrum; Time domain; Feature (linguistics); Pattern recognition (psychology); Artificial intelligence; Domain (mathematical analysis); Cepstrum; Speech processing; Audio signal flow; Digital signal processing; Speech coding; Computer vision; Mathematics","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":[0.0003295117,0.0001262582,0.000163996,0.0001649469,0.00005309463,0.0001063802,0.0003645725,0.0001196679,0.00009251322],"category_scores_gemma":[0.00000643448,0.000116511,0.00003372699,0.000603421,0.00001732094,0.0001919772,0.000104102,0.0002963532,0.00006942716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004768755,"about_ca_system_score_gemma":0.00004073763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002547702,"about_ca_topic_score_gemma":7.948317e-7,"domain_scores_codex":[0.9990594,0.00002621136,0.0001451807,0.0003302742,0.0001846672,0.0002542102],"domain_scores_gemma":[0.9994407,0.0001027066,0.00008951618,0.0002932575,0.00002420337,0.00004957971],"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":[0.000006069589,0.0000382812,0.0001009992,0.00002172465,0.000005764371,0.000006435833,0.0003262133,0.003515391,0.1727066,0.008189461,0.0050599,0.8100232],"study_design_scores_gemma":[0.002439076,0.0001453702,0.03189875,0.0001197298,0.00005903209,0.00007913091,0.0003688238,0.8111495,0.06198499,0.02718617,0.06296988,0.001599515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005785337,0.00006142554,0.9638512,0.0003833492,0.0003490521,0.00006581475,6.340434e-7,0.0001021593,0.02940101],"genre_scores_gemma":[0.6232979,0.000003514883,0.3745505,0.0005985815,0.00009970498,0.000006089047,0.000002898814,0.000008112584,0.001432702],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8084236,"threshold_uncertainty_score":0.4751181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01591782837905122,"score_gpt":0.3086868783877196,"score_spread":0.2927690500086684,"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."}}