{"id":"W3039319660","doi":"10.1007/978-3-030-59716-0_45","title":"Ultra2Speech - A Deep Learning Framework for Formant Frequency Estimation and Tracking from Ultrasound Tongue Images","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Formant; Computer science; Vocal tract; Vowel; Speech recognition; Feature (linguistics); Artificial intelligence; Annotation; Deep learning; Pattern recognition (psychology); Computer vision","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":[0.000877029,0.0011454,0.0008970786,0.0005872096,0.0004107424,0.000974734,0.001886076,0.00175963,0.008090335],"category_scores_gemma":[0.001346339,0.0007123995,0.0009966082,0.0005357527,0.0003242287,0.001110744,0.001942634,0.001842807,0.005252048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004637438,"about_ca_system_score_gemma":0.0008550606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006239535,"about_ca_topic_score_gemma":0.01387761,"domain_scores_codex":[0.9996623,0.0000676955,0.00001566357,0.0001074875,0.00009085965,0.00005607724],"domain_scores_gemma":[0.9996138,0.0001648056,0.00002277046,0.00007239619,0.00009153352,0.00003470403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004830823,0.0002180612,0.0009202785,0.0001849638,0.0001784162,0.0001727578,0.00007307634,0.08224127,0.03654982,0.004723737,0.01492892,0.8593255],"study_design_scores_gemma":[0.0000188022,0.00006795281,0.000469865,0.0000171948,0.00002037601,0.00006378063,0.00001114916,0.9829766,0.009924334,0.003085473,0.003328355,0.00001614926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009710122,0.00065673,0.9801342,0.0001319447,0.0001333173,0.00005256526,0.0008560886,0.007116853,0.001208164],"genre_scores_gemma":[0.2003927,0.00088859,0.7680671,0.0004344881,0.0002119201,0.0003308926,0.005864258,0.001301166,0.02250892],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008090335,"threshold_uncertainty_score":0.02706492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01852541004008515,"score_gpt":0.2842986438698576,"score_spread":0.2657732338297725,"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."}}