{"id":"W101223626","doi":"10.21437/interspeech.2010-466","title":"Identifying articulatory goals from kinematic data using principal differential analysis","year":2010,"lang":"en","type":"article","venue":"","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Kinematics; Computer science; Principal component analysis; Principal (computer security); Differential (mechanical device); Baseline (sea); Speech recognition; Artificial neural network; Artificial intelligence; Pattern recognition (psychology); Engineering","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":[0.0008894242,0.0007560786,0.0005583887,0.00168123,0.0003378905,0.0009840244,0.0003642612,0.0004894121,0.001296981],"category_scores_gemma":[0.003968632,0.0004425641,0.0005367995,0.001060468,0.0004658747,0.0008677201,0.0006487623,0.000803925,0.001103316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002477102,"about_ca_system_score_gemma":0.0004677584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001073109,"about_ca_topic_score_gemma":0.001957089,"domain_scores_codex":[0.9995739,0.00009372483,0.00002399256,0.0001229309,0.0001382118,0.00004724679],"domain_scores_gemma":[0.9989164,0.0005797029,0.0001409822,0.0001375942,0.000168091,0.00005714589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003387851,0.0001731588,0.02485862,0.0003074617,0.0001591746,0.0002554077,0.0004704543,0.06438022,0.1303865,0.004263575,0.002254996,0.7721517],"study_design_scores_gemma":[0.00002500336,0.0001490276,0.05907435,0.00004582868,0.00003493225,0.0004385342,0.0001979319,0.8895306,0.03407486,0.01353283,0.002801919,0.00009417094],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1710669,0.0002355892,0.8250741,0.0001156172,0.00003223219,0.0001126309,0.0003426607,0.00100386,0.002016459],"genre_scores_gemma":[0.7664737,0.0002674893,0.2308847,0.00002512584,0.00002154812,0.0001159146,0.0006857947,0.0001501335,0.001375608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00168123,"threshold_uncertainty_score":0.00470376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1833606443558684,"score_gpt":0.448600686906081,"score_spread":0.2652400425502126,"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."}}