{"id":"W4395081477","doi":"10.18280/ria.380203","title":"HERF: A Machine Learning Framework for Automatic Emotion Recognition from Audio","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Emotion recognition; Human–computer interaction; Multimedia","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004340596,0.0001886533,0.0002060108,0.0001834445,0.0001874982,0.0001275115,0.0001264004,0.0002359393,0.01004739],"category_scores_gemma":[0.0003158219,0.0001918424,0.0001973858,0.0003773293,0.00004958931,0.0001401628,0.00002275877,0.0004361563,0.008852908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006200676,"about_ca_system_score_gemma":0.00002080272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008686761,"about_ca_topic_score_gemma":0.00001851497,"domain_scores_codex":[0.9984038,0.0001511035,0.0004700844,0.000539682,0.0001165051,0.0003188239],"domain_scores_gemma":[0.9987208,0.0007447304,0.0001013691,0.0002532455,0.0000911036,0.00008876481],"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":[0.0000424156,0.0001902302,0.00007915424,0.0001858191,0.0001055064,0.00001916461,0.006530676,0.0004356325,0.00121056,0.01047816,0.001545879,0.9791768],"study_design_scores_gemma":[0.000139187,0.0004926012,0.0002124886,0.001773411,0.0001774411,0.00006303051,0.00466051,0.7442813,0.01484995,0.1973997,0.03538249,0.0005679164],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09525277,0.001738579,0.890238,0.001147474,0.003548848,0.0006116302,0.00009452736,0.0007091729,0.006658933],"genre_scores_gemma":[0.9800866,0.0001444215,0.01120307,0.0002286991,0.0007315775,0.0002162309,0.0005591985,0.00006554338,0.006764677],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9786089,"threshold_uncertainty_score":0.9919188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08165513349018866,"score_gpt":0.343949219025481,"score_spread":0.2622940855352923,"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."}}