{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009754497,0.0004692397,0.0005937769,0.001080374,0.0006823074,0.001084654,0.0008352606,0.001385913,0.002020356],"category_scores_gemma":[0.03011975,0.0002316504,0.000794855,0.0004079885,0.0006479124,0.001124228,0.001048488,0.0008090883,0.001083813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005439944,"about_ca_system_score_gemma":0.0006401864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001511876,"about_ca_topic_score_gemma":0.002747331,"domain_scores_codex":[0.9923989,0.002899509,0.000968235,0.0008627888,0.002558098,0.0003125413],"domain_scores_gemma":[0.9693444,0.01684784,0.003433849,0.001645378,0.008037765,0.000690719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00618257,0.003823233,0.788027,0.0004467513,0.0005848455,0.0001963207,0.005663346,0.001822749,0.02375627,0.001057628,0.003605528,0.1648338],"study_design_scores_gemma":[0.0003767369,0.005478336,0.9568332,0.0001070685,0.0002898739,0.0004446694,0.002480539,0.01496504,0.01401318,0.000635216,0.004257895,0.00011842],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9792556,0.0002139527,0.01074951,0.0002133785,0.0002535034,0.001010395,0.0007574558,0.0001198427,0.007426268],"genre_scores_gemma":[0.9860567,0.00009917206,0.009698748,0.0002219181,0.00007921766,0.001358392,0.000604337,0.00004735041,0.001834108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009754497,"threshold_uncertainty_score":0.05158728,"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."}}