{"id":"W7127400876","doi":"10.1109/ccece64018.2025.11364356","title":"Integrating Speech and Pupillometry for Enhanced Emotion Recognition: A Multimodal Approach","year":2025,"lang":"","type":"article","venue":"","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pupillometry; Modalities; Noise (video); Support vector machine; Random forest; Emotion recognition; Pattern recognition (psychology); Mixture model","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":[0.001037504,0.0006542497,0.0006873174,0.0009448311,0.0002507384,0.0008020607,0.0004321579,0.0006803883,0.003124023],"category_scores_gemma":[0.001654584,0.000205167,0.0005822073,0.0004103798,0.0002029411,0.0009535526,0.0006448824,0.0004135141,0.001335521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001512267,"about_ca_system_score_gemma":0.0001787733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003833713,"about_ca_topic_score_gemma":0.0007041728,"domain_scores_codex":[0.9993631,0.0001888172,0.00003105291,0.000187887,0.0001694727,0.00005961524],"domain_scores_gemma":[0.999388,0.0002387798,0.00006226727,0.00006123701,0.0002179504,0.00003183154],"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":[0.0007943614,0.0002931009,0.008742426,0.0003621841,0.0001860497,0.0002568392,0.000297825,0.002888795,0.3557785,0.001082887,0.002142797,0.6271742],"study_design_scores_gemma":[0.0001632919,0.002545805,0.08385702,0.0002712528,0.0008847739,0.004047506,0.000595518,0.4676569,0.4108805,0.006647567,0.02212595,0.0003239631],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1391919,0.00178977,0.8502307,0.0004654258,0.0002347768,0.0002635626,0.0003864319,0.002573001,0.004864496],"genre_scores_gemma":[0.5794654,0.0008936428,0.4144338,0.0003689861,0.0002965424,0.0002438326,0.0003033114,0.0001560582,0.00383844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003124023,"threshold_uncertainty_score":0.0104509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03940183501990691,"score_gpt":0.3335246884656337,"score_spread":0.2941228534457268,"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."}}