{"id":"W2153767712","doi":"10.1073/pnas.0705369104","title":"Unsupervised learning of vowel categories from infant-directed speech","year":2007,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Language Development and Disorders","field":"Psychology","cited_by":292,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada","keywords":"Vowel; Computer science; Language acquisition; Artificial intelligence; Speech recognition; Natural language processing; Vowel length; Psychology","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":[0.001274822,0.00007967592,0.0001464405,0.0001894059,0.0001090032,0.000009699718,0.0005495867,0.00009448911,0.0002522736],"category_scores_gemma":[0.000572528,0.00005449621,0.00005202839,0.000842845,0.0005784617,0.0002012274,0.00007798407,0.000151903,0.000003831491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001278781,"about_ca_system_score_gemma":0.00002599088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002305134,"about_ca_topic_score_gemma":0.000001158324,"domain_scores_codex":[0.9985483,0.000006545535,0.0003432776,0.0001862735,0.0007553264,0.0001603203],"domain_scores_gemma":[0.9991419,0.0002040998,0.0003692717,0.00000679697,0.0002531543,0.00002478347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001714464,0.0001536664,0.5823476,0.00005700421,0.0001141139,6.44477e-8,0.02387131,0.00001655793,0.3295249,0.05518436,0.002513506,0.006045471],"study_design_scores_gemma":[0.0003405201,0.00002869223,0.7873809,0.00003459144,0.00001154052,0.000001949184,0.005214752,0.0000610106,0.188242,0.0182923,0.0003010751,0.00009064046],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9562976,0.0002596401,0.000002221565,0.0004877062,0.00004557808,0.00009433761,0.000005684547,0.00002303157,0.04278415],"genre_scores_gemma":[0.9975832,0.000008097852,0.001668546,0.0001213756,0.0000457501,0.00000233268,6.367422e-7,0.000003744077,0.0005663612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2050333,"threshold_uncertainty_score":0.2762219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03164387330461199,"score_gpt":0.3209974641940448,"score_spread":0.2893535908894329,"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."}}