{"id":"W3039097787","doi":"10.5573/ieiespc.2020.9.3.185","title":"Adaptive Feature Generation for Speech Emotion Recognition","year":2020,"lang":"en","type":"article","venue":"IEIE Transactions on Smart Processing and Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; Artificial intelligence; Classifier (UML); Feature (linguistics); Principal component analysis; Pattern recognition (psychology); Emotion recognition; Correlation; Emotion classification; Cepstrum; Sentiment analysis; Feature extraction; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001922462,0.0001537585,0.0001537785,0.00009517819,0.000622845,0.00030478,0.0001263375,0.00009277698,0.000008517236],"category_scores_gemma":[0.00002076967,0.0001544905,0.0000726541,0.0003256464,0.00002462491,0.0004121923,0.0000038567,0.0001799583,0.00001624774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002572497,"about_ca_system_score_gemma":0.00004198981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003430994,"about_ca_topic_score_gemma":0.000003312849,"domain_scores_codex":[0.998935,0.00005623169,0.0001862576,0.0004649047,0.0001666488,0.000190931],"domain_scores_gemma":[0.9994296,0.00009155547,0.00009490606,0.00009573462,0.0001755509,0.0001125863],"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":[0.00002021298,0.00003804023,0.000002537854,0.00003243066,0.00001097994,0.000001599935,0.0008138001,0.0001731023,0.001332087,0.00002709192,0.0001252609,0.9974229],"study_design_scores_gemma":[0.0004511265,0.0002224357,0.00005937163,0.00009815276,0.0000259002,0.00003429121,0.0002088432,0.977486,0.02014948,0.0004316541,0.0006084486,0.0002242815],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01924195,0.0000647553,0.976086,0.003540017,0.0001914629,0.0002286124,0.000008599963,0.0003162156,0.0003223818],"genre_scores_gemma":[0.7247434,0.0000125614,0.2738372,0.001165132,0.0001631674,0.00001462474,0.000009718129,0.00001208266,0.00004209525],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9971986,"threshold_uncertainty_score":0.629994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07397113750810175,"score_gpt":0.2624858273158806,"score_spread":0.1885146898077789,"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."}}