{"id":"W4413952314","doi":"10.37965/jait.2025.0781","title":"A Multimodal Framework for Speech Emotion Recognition in Low-Resource Languages","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Technology","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Resource (disambiguation); Emotion recognition; Speech recognition; Linguistics; Natural language processing","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":[0.0004018388,0.00009286592,0.000205466,0.0009540715,0.00005502846,0.00002014746,0.0001094915,0.000364546,0.0001281793],"category_scores_gemma":[0.0005133262,0.00008724779,0.0000611092,0.0005163161,0.0001115242,0.00006775602,0.00001990441,0.0003902728,0.00002539696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002865632,"about_ca_system_score_gemma":0.00002615481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001234058,"about_ca_topic_score_gemma":0.00005120829,"domain_scores_codex":[0.9990355,0.00005027171,0.000509813,0.0001595224,0.00006410761,0.0001808128],"domain_scores_gemma":[0.999271,0.0001992133,0.0002127629,0.0000971637,0.0001913981,0.00002845355],"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":[0.0002060253,0.000268123,0.0004691141,0.00002576886,0.0000324083,0.00002543191,0.0004376819,0.000005998343,0.001265304,0.05925028,0.0001391092,0.9378747],"study_design_scores_gemma":[0.000280106,0.0006375993,0.0006589371,0.0006496562,0.0000510654,0.000143877,0.01763028,0.0004997196,0.07355098,0.9046373,0.001099352,0.0001611435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6837835,0.0004314157,0.309731,0.004035745,0.0006670707,0.0002644224,0.000006596575,0.00003973314,0.001040569],"genre_scores_gemma":[0.9896253,0.00007736781,0.009777875,0.0002415584,0.0001462611,0.00001471956,0.000004894804,0.000008042767,0.0001040028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9377136,"threshold_uncertainty_score":0.3557862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04212576809165484,"score_gpt":0.3665315492201432,"score_spread":0.3244057811284884,"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."}}