{"id":"W4392945955","doi":"10.1109/icmla58977.2023.00081","title":"Iterative Feature Boosting for Explainable Speech Emotion Recognition","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Ethica (Canada); Université du Québec à Montréal","funders":"","keywords":"Boosting (machine learning); Computer science; Emotion recognition; Speech recognition; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Linguistics","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005740853,0.0003358555,0.0003416277,0.000336229,0.000208871,0.0001387855,0.000142987,0.0008831091,0.001907383],"category_scores_gemma":[0.0002501034,0.000335923,0.0002689243,0.0001651213,0.00002922769,0.0001104656,0.0001455361,0.0007154477,0.001910139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001128048,"about_ca_system_score_gemma":0.00004827217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001092086,"about_ca_topic_score_gemma":0.00008712149,"domain_scores_codex":[0.9980141,0.0001880147,0.000367905,0.0008418261,0.00017301,0.0004151639],"domain_scores_gemma":[0.9985381,0.0002491231,0.0003016632,0.0003393173,0.0004810009,0.00009075461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003318574,0.0004055752,0.0001433183,0.0009510392,0.000498254,0.00006463132,0.006783094,0.0000345299,0.0005033365,0.002501277,0.6297725,0.3580106],"study_design_scores_gemma":[0.01512533,0.00256909,0.01690744,0.007798666,0.001681341,0.0004947041,0.0530904,0.006787293,0.03119867,0.7257994,0.1313198,0.007227837],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.1471611,0.0003642077,0.2418706,0.01310083,0.03856683,0.01119327,0.002467172,0.004553119,0.5407229],"genre_scores_gemma":[0.1487226,0.000176187,0.06034741,0.00259281,0.006067523,0.004253267,0.03544824,0.0004423568,0.7419496],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7232981,"threshold_uncertainty_score":0.9999093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1308116065560525,"score_gpt":0.3671673718836944,"score_spread":0.2363557653276419,"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."}}