{"id":"W4413372625","doi":"10.1250/ast.e25.42","title":"Quantitative analysis of singing expression and facial gestures using image recognition with artificial intelligence","year":2025,"lang":"en","type":"article","venue":"Nippon Onkyo Gakkaishi/Acoustical science and technology/Nihon Onkyo Gakkaishi","topic":"Educational Technology and Pedagogy","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Education and Early Childhood Development","funders":"Japan Society for the Promotion of Science","keywords":"Singing; Gesture; Facial expression; Artificial intelligence; Speech recognition; Expression (computer science); Pattern recognition (psychology); Computer science; Image (mathematics); Computer vision; Communication; Psychology; Acoustics","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":[0.0004643055,0.0003654069,0.0003637555,0.001914309,0.000171445,0.0004548782,0.000210396,0.0002987891,0.00165186],"category_scores_gemma":[0.001245919,0.0001238978,0.0003088582,0.001050326,0.0003402034,0.0004328392,0.0002888077,0.0002522221,0.0004621516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001907217,"about_ca_system_score_gemma":0.0001461524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009491746,"about_ca_topic_score_gemma":0.001035922,"domain_scores_codex":[0.999541,0.00007371361,0.00002792338,0.00009089942,0.0002253929,0.0000410626],"domain_scores_gemma":[0.9995459,0.0001626561,0.00008326736,0.00004097068,0.0001420092,0.00002509781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0004130379,0.0001253224,0.02022718,0.0005116009,0.0000983359,0.0002166143,0.0005038821,0.008016136,0.5293535,0.0008971017,0.0008130907,0.4388242],"study_design_scores_gemma":[0.00004078124,0.001013759,0.4568415,0.0001107376,0.0002295434,0.001852768,0.001642637,0.3107349,0.2198284,0.001888535,0.005613775,0.0002027195],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7298481,0.001086194,0.2576056,0.0001432512,0.00009313663,0.0003347037,0.0009517818,0.001002459,0.008934757],"genre_scores_gemma":[0.8968041,0.0004489553,0.09982604,0.00004028265,0.00004427797,0.0002324489,0.0004586047,0.0000582395,0.00208704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001914309,"threshold_uncertainty_score":0.005526006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04359240028760244,"score_gpt":0.3506230857921549,"score_spread":0.3070306855045525,"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."}}