{"id":"W4414462895","doi":"10.1109/jiot.2025.3613687","title":"Leveraging Cross-Attention Transformer and Multifeature Fusion for Cross-Linguistic Speech Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Mel-frequency cepstrum; Transformer; Feature extraction; Emotion recognition; Speech processing; Training set; Cepstrum; Acoustic model; Speech corpus","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001990365,0.001326081,0.0009394193,0.001501921,0.0003817162,0.001017447,0.001029331,0.0008304229,0.002292644],"category_scores_gemma":[0.002454229,0.0003357444,0.001239827,0.0008590193,0.0004048138,0.00205494,0.002283857,0.001256916,0.001229486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005578336,"about_ca_system_score_gemma":0.0004718497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003068514,"about_ca_topic_score_gemma":0.003443841,"domain_scores_codex":[0.9992084,0.0001559804,0.00004436404,0.0002937861,0.0001682947,0.0001292379],"domain_scores_gemma":[0.9992913,0.0002301303,0.00004232128,0.0001169276,0.0002679357,0.00005138301],"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":[0.0005036545,0.0004956197,0.003411002,0.0001377926,0.0002694357,0.0002280639,0.0002541738,0.03182498,0.1015147,0.002209515,0.003219529,0.8559316],"study_design_scores_gemma":[0.00002077266,0.0002256907,0.00550894,0.00001751475,0.0001552774,0.0001788385,0.0001248308,0.9341948,0.05385811,0.003487338,0.002184367,0.00004352038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09851108,0.001192326,0.8912996,0.000301868,0.0002123299,0.0001289954,0.0001949333,0.003895208,0.004263688],"genre_scores_gemma":[0.7995667,0.0005311959,0.1931111,0.0003706015,0.000122399,0.0001086732,0.000999925,0.0002412716,0.004948149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003068514,"threshold_uncertainty_score":0.01052618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02069736530307698,"score_gpt":0.3086427649824087,"score_spread":0.2879453996793317,"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."}}