{"id":"W2052896603","doi":"10.1121/1.4808875","title":"Learning to categorize lexical tones in sentences with variable narrow focus: A neural network approach","year":2006,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Focus (optics); Categorization; Mandarin Chinese; Computer science; Tone (literature); Speech recognition; Perception; Syllable; Artificial neural network; Utterance; Psychology; Artificial intelligence; 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":[0.0004783684,0.0005788118,0.0004186564,0.0004364656,0.0002460923,0.0007142908,0.0008444975,0.00090718,0.0008006595],"category_scores_gemma":[0.001050745,0.0003855232,0.0004381042,0.0002238885,0.0003880378,0.000999704,0.0005314007,0.0008511486,0.0001449496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007408282,"about_ca_system_score_gemma":0.0002977222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003532741,"about_ca_topic_score_gemma":0.004077205,"domain_scores_codex":[0.9998881,0.00002121531,0.000006562745,0.00004872325,0.0000126125,0.00002276774],"domain_scores_gemma":[0.9997373,0.0001528449,0.00002986764,0.0000192238,0.00003918003,0.00002151925],"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":[0.000799445,0.0007170834,0.01899393,0.0002199258,0.0004713209,0.0003471927,0.0007292613,0.5508706,0.08219439,0.00600634,0.001278973,0.3373715],"study_design_scores_gemma":[0.00000709153,0.0000535727,0.001610407,0.000005015969,0.00001820461,0.00001754273,0.000038921,0.9935587,0.002078321,0.002506602,0.00009751855,0.00000811333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7729888,0.0009598079,0.2208894,0.0008951147,0.0000535504,0.0001182838,0.0001506727,0.0004424799,0.003501945],"genre_scores_gemma":[0.9621857,0.000217671,0.03581314,0.00008278578,0.00002374518,0.00006478038,0.0001438532,0.0000149811,0.001453399],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003532741,"threshold_uncertainty_score":0.007024348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01663164830700493,"score_gpt":0.2821461339671853,"score_spread":0.2655144856601804,"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."}}