{"id":"W4244748443","doi":"10.31234/osf.io/xp6k2","title":"Automatic word count estimation from daylong child-centered recordings in various language environments using language-independent syllabification of speech","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Syllable; Word (group theory); Speech recognition; Syllabification; Phonotactics; Natural language processing; Artificial intelligence; Mathematics; Linguistics","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":[0.001101213,0.001328182,0.001144251,0.002438993,0.0003010563,0.001158162,0.0009675029,0.0009713771,0.004664797],"category_scores_gemma":[0.004103342,0.0003514358,0.0005445794,0.001225122,0.0003808536,0.001569925,0.001460794,0.0007330264,0.006599315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003168215,"about_ca_system_score_gemma":0.0005982918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002602139,"about_ca_topic_score_gemma":0.005012821,"domain_scores_codex":[0.9985297,0.0002143317,0.0001267826,0.0006093655,0.0004105959,0.000109326],"domain_scores_gemma":[0.9972286,0.00107614,0.0002288415,0.0003030221,0.001019378,0.0001439838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007242961,0.0002248756,0.01312143,0.0009460482,0.0002076083,0.0006000504,0.0008695707,0.003321011,0.2459422,0.0007657377,0.01017734,0.7230998],"study_design_scores_gemma":[0.0002521202,0.0009767236,0.2271203,0.0003465063,0.0003610973,0.003851064,0.002283995,0.3443592,0.3769926,0.003843319,0.03905594,0.0005571209],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4624056,0.001903405,0.4713604,0.0002386851,0.0004956206,0.0008584297,0.01380603,0.0404995,0.00843244],"genre_scores_gemma":[0.4180342,0.0009906486,0.5389751,0.0002279758,0.000188092,0.001370492,0.03027436,0.001791325,0.008147918],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004664797,"threshold_uncertainty_score":0.01560533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01606227370194699,"score_gpt":0.2556369938349796,"score_spread":0.2395747201330326,"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."}}