{"id":"W4390413794","doi":"10.1016/j.jvoice.2023.12.008","title":"Validation of an AI-assisted Treatment Outcome Measure for Gender-Affirming Voice Care: Comparing AI Accuracy to Listener’s Perception of Voice Femininity","year":2023,"lang":"en","type":"article","venue":"Journal of Voice","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"National Center for Advancing Translational Sciences; National Institutes of Health","keywords":"Femininity; Psychology; Perception; Voice analysis; Audiology; Quality (philosophy); Transgender; Speech recognition; Computer science; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.0007835102,0.000249851,0.0008765688,0.000482349,0.0001234566,0.00003241861,0.0002190076,0.0001550086,0.00001274562],"category_scores_gemma":[0.0009455379,0.0002104152,0.0004043437,0.0005721897,0.0000378468,0.0004390025,0.0000392447,0.0002719461,0.00001479619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003776674,"about_ca_system_score_gemma":0.0002968155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002695915,"about_ca_topic_score_gemma":0.0003221288,"domain_scores_codex":[0.997415,0.0001306617,0.001164872,0.0002524984,0.0007262875,0.0003106874],"domain_scores_gemma":[0.9967881,0.0003156615,0.0008572643,0.0003570177,0.001413914,0.0002679919],"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":[0.00559649,0.003426037,0.3533021,0.003132964,0.001503151,0.0001086988,0.04815753,0.007474707,0.4688094,0.00002290755,0.004453132,0.1040129],"study_design_scores_gemma":[0.01029373,0.005571394,0.8950884,0.0008653003,0.002274536,0.0002303825,0.04795203,0.001883491,0.03027156,0.00004296838,0.005049212,0.0004769982],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955828,0.0001197535,0.001140846,0.001893432,0.0003636954,0.0005876039,0.00004410243,0.00003988864,0.0002278798],"genre_scores_gemma":[0.9962671,0.00004538994,0.002664621,0.0003899007,0.0003495137,0.00001344476,0.0001040366,0.00003971829,0.0001263128],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5417863,"threshold_uncertainty_score":0.8580483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1464894277765302,"score_gpt":0.4051974181307093,"score_spread":0.2587079903541791,"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."}}