{"id":"W4409494345","doi":"10.1109/icarc64760.2025.10963219","title":"Enhancing Human Emotion Detection in Audio Data with Deep Neural Networks Using Cross-Dataset","year":2025,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial neural network; Deep neural networks; Emotion recognition; Artificial intelligence; Emotion detection; Speech recognition","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":[0.0003504727,0.0001099907,0.0001170411,0.0001244894,0.0003060066,0.0004602977,0.0006783405,0.00005168108,0.00001073076],"category_scores_gemma":[0.000016671,0.00009396025,0.00001038137,0.0006560714,0.00003856018,0.001542823,0.0005174492,0.0001676152,0.000001349345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005716878,"about_ca_system_score_gemma":0.00004118108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002795229,"about_ca_topic_score_gemma":0.001508892,"domain_scores_codex":[0.9988941,0.00004209534,0.0002196393,0.0004754729,0.0001210752,0.000247637],"domain_scores_gemma":[0.9991549,0.00002678242,0.00007857868,0.000676182,0.00003272522,0.00003087253],"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":[0.00004908795,0.0001725737,0.01869749,0.0002392591,0.00004913101,0.00008458954,0.000559844,0.2763753,0.02872803,0.001890855,0.001267947,0.6718858],"study_design_scores_gemma":[0.0002490592,0.00001616671,0.004883587,0.00006473954,0.000005053994,0.0000109255,0.00001727014,0.9901841,0.004192386,0.0001380079,0.0001228662,0.0001158906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1350702,0.00004362638,0.8642539,0.00006801958,0.0001826501,0.00007168845,0.00000280937,0.00007233382,0.0002347822],"genre_scores_gemma":[0.9815958,8.331969e-7,0.01755797,0.0006299157,0.00006698391,0.000001763803,0.00009278325,0.000004782609,0.00004921457],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.846696,"threshold_uncertainty_score":0.4438661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03110184901904365,"score_gpt":0.3172033544056031,"score_spread":0.2861015053865594,"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."}}