{"id":"W4417073360","doi":"10.1145/3743093.3771083","title":"Robust speech emotion recognition using conditional transformer-based architecture","year":2025,"lang":"","type":"article","venue":"","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Intertek (Canada)","funders":"","keywords":"Robustness (evolution); Speech enhancement; Noise measurement; Transformer; Noise (video); Speech processing; Feature extraction; Pattern recognition (psychology)","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":[0.0006057771,0.0005795947,0.0005130856,0.001220864,0.0005769294,0.0001443841,0.0001990703,0.0009348994,0.04041215],"category_scores_gemma":[0.00007430804,0.0006251557,0.0005219938,0.001108585,0.0003106252,0.0001939417,0.00001474169,0.0009236695,0.001129653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002756355,"about_ca_system_score_gemma":0.0004901382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000177189,"about_ca_topic_score_gemma":0.0002012834,"domain_scores_codex":[0.9960915,0.0006874914,0.001034786,0.001014391,0.0004288139,0.0007430338],"domain_scores_gemma":[0.9984599,0.0002438783,0.0002654178,0.000384203,0.0004337758,0.0002128671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00156514,0.004013374,0.0004258349,0.00108185,0.0009166153,0.0000736977,0.001004952,0.006577402,0.0111901,0.005690414,0.0123305,0.9551301],"study_design_scores_gemma":[0.09048048,0.00500646,0.03405721,0.01199704,0.008932145,0.001883326,0.01745393,0.1795497,0.2260419,0.3090918,0.1052893,0.01021669],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09248265,0.0001950238,0.6923481,0.003806348,0.003874689,0.001305625,0.0005318399,0.0002348819,0.2052209],"genre_scores_gemma":[0.9625251,0.00007723566,0.01899978,0.006652674,0.0006555347,0.00005894247,0.003912425,0.00007391025,0.007044358],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9449134,"threshold_uncertainty_score":0.9996481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0819833324037891,"score_gpt":0.3263126824916147,"score_spread":0.2443293500878256,"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."}}