{"id":"W2170950676","doi":"10.1109/icassp.2005.1415607","title":"Recognizing Human Emotion from Audiovisual Informaiton","year":2006,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mel-frequency cepstrum; Computer science; Formant; Mahalanobis distance; Speech recognition; Artificial intelligence; Feature extraction; Pattern recognition (psychology); Face (sociological concept); Emotion classification; Feature selection; Facial expression; Hidden Markov model; Feature (linguistics); Cepstrum; Facial recognition system; Vowel","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":[0.0001698923,0.0003252311,0.0002866638,0.0005854333,0.0001154013,0.0006745025,0.0002276145,0.0003244616,0.002059333],"category_scores_gemma":[0.001085119,0.0000771776,0.0001722934,0.0003139898,0.0001651514,0.0004527164,0.000286217,0.000160878,0.001159278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001296003,"about_ca_system_score_gemma":0.00008946998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006664454,"about_ca_topic_score_gemma":0.0006824106,"domain_scores_codex":[0.9998466,0.00001739991,0.000006793938,0.000032003,0.00007612308,0.0000209854],"domain_scores_gemma":[0.9997444,0.00007399304,0.00002863294,0.00001951308,0.0001183856,0.00001512893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004670929,0.00007906668,0.003663993,0.0003719059,0.00004899694,0.0003141535,0.0001829087,0.002494426,0.3679158,0.0008864736,0.003659633,0.6199155],"study_design_scores_gemma":[0.0001139724,0.001076098,0.1143605,0.000377345,0.000504981,0.003630465,0.001424945,0.2330972,0.5724748,0.007174151,0.06557728,0.0001882641],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4591174,0.006784105,0.4979801,0.0008212052,0.001051467,0.0002112035,0.001598012,0.003347371,0.02908907],"genre_scores_gemma":[0.8832094,0.003297719,0.100443,0.0004015139,0.0004710204,0.0000976293,0.001465937,0.0001125392,0.01050122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002059333,"threshold_uncertainty_score":0.006889164,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01302526757027436,"score_gpt":0.2373536813925012,"score_spread":0.2243284138222269,"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."}}