{"id":"W2027324763","doi":"10.1121/1.2982369","title":"A linear model of acoustic-to-facial mapping: Model parameters, data set size, and generalization across speakers","year":2008,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Canada Research Chairs","keywords":"Computer science; Predictability; Speech recognition; Perception; Set (abstract data type); Linear model; Generalization; Correlation; Transformation (genetics); Mathematics; Machine learning; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006602813,0.0001424422,0.000341441,0.0000160097,0.0002815204,0.00002957595,0.001879524,0.00006150886,0.000001327041],"category_scores_gemma":[0.0004321362,0.00008421647,0.0001479338,0.0004091171,0.0005931836,0.0003262662,0.0009993713,0.0002726105,5.449422e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002985366,"about_ca_system_score_gemma":0.0002176192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001797515,"about_ca_topic_score_gemma":3.671722e-7,"domain_scores_codex":[0.9983892,0.00007219971,0.0004902397,0.0001753829,0.0005946159,0.0002783988],"domain_scores_gemma":[0.9981997,0.0002618988,0.0005551126,0.0006211088,0.0002369186,0.0001252841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004579786,0.00005252453,0.00006295559,0.00003011879,0.0000667682,7.28353e-7,0.005031218,0.9090793,0.0752944,0.000001354372,0.005698591,0.004636233],"study_design_scores_gemma":[0.0002850958,0.00008233195,0.0001295271,0.00004828141,0.00005851099,0.00005956371,0.0004503954,0.9928858,0.005180871,0.0006813955,0.00003993793,0.00009829421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1534765,0.00008860672,0.843779,0.002462418,0.0000608947,0.00007744638,0.00003726303,0.000009237266,0.000008565119],"genre_scores_gemma":[0.4474725,0.0002818696,0.5508125,0.001346281,0.00005071033,2.487517e-7,5.044566e-7,0.000007332926,0.00002802513],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2939959,"threshold_uncertainty_score":0.3492654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0668483365301081,"score_gpt":0.2970498218997159,"score_spread":0.2302014853696078,"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."}}