{"id":"W4389752793","doi":"10.1016/j.eswa.2023.122946","title":"MSER: Multimodal speech emotion recognition using cross-attention with deep fusion","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":137,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Ministry of Science and ICT, South Korea; State Fund for Fundamental Research of Ukraine","keywords":"Computer science; Discriminative model; Robustness (evolution); Speech recognition; Artificial intelligence; Encoder; Feature (linguistics); Fusion mechanism; Pattern recognition (psychology); Fusion","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003128464,0.0002551213,0.0002325484,0.0003543947,0.0005398598,0.0001301178,0.0001343006,0.0002229298,0.0003690347],"category_scores_gemma":[0.000008960645,0.0002122705,0.00006796043,0.001005002,0.0001039044,0.0002735423,0.00002574764,0.0001841652,0.002528909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001228846,"about_ca_system_score_gemma":0.00003616169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006136834,"about_ca_topic_score_gemma":0.00007181006,"domain_scores_codex":[0.9980136,0.0001556867,0.000429351,0.0006428471,0.0003609484,0.0003975989],"domain_scores_gemma":[0.9986074,0.00005780883,0.0002881275,0.0004951101,0.0004014934,0.0001500364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002696046,0.005420865,0.06503334,0.001151508,0.001607767,0.0002660374,0.02137829,0.006449998,0.1465389,0.01009155,0.01588441,0.7234813],"study_design_scores_gemma":[0.03757297,0.003621973,0.5465398,0.004173612,0.0009523769,0.007237662,0.08965924,0.1932245,0.006974395,0.002190033,0.09976115,0.008092333],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7274016,0.0001675091,0.2557908,0.0001891662,0.0007823617,0.002984157,0.00006450673,0.001086736,0.01153313],"genre_scores_gemma":[0.9880592,0.00003543074,0.004532454,0.00009499896,0.0007419722,0.002639259,0.001467805,0.00009402628,0.002334878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.715389,"threshold_uncertainty_score":0.9982477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05091831193250718,"score_gpt":0.3489223053887625,"score_spread":0.2980039934562553,"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."}}