{"id":"W2728212668","doi":"10.1017/cnj.2017.15","title":"Low-level articulatory synthesis: A working text-to-speech solution and a linguistic tool","year":2017,"lang":"en","type":"article","venue":"The Canadian Journal of Linguistics / La revue canadienne de linguistique","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Vocal tract; Speech synthesis; Computer science; Intonation (linguistics); Linguistics; Formant; Speech recognition; License; Cued speech; Prosody; Speech production; Parsing; Artificial intelligence; Natural language processing; Vowel","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":[0.001446196,0.001107271,0.00123772,0.001274982,0.000762141,0.003930899,0.001989216,0.001237073,0.02400843],"category_scores_gemma":[0.003092707,0.0004911476,0.0006974692,0.0006946804,0.001327055,0.002556172,0.001980001,0.0008357988,0.01172088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004491208,"about_ca_system_score_gemma":0.0005748661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004923923,"about_ca_topic_score_gemma":0.0003229244,"domain_scores_codex":[0.9992066,0.0001748108,0.0001034439,0.0003151018,0.0001669841,0.00003315107],"domain_scores_gemma":[0.9985055,0.0005931336,0.00005434555,0.0003946676,0.000361163,0.00009123005],"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":[0.0005483717,0.000178265,0.000874473,0.0008595192,0.0001060301,0.0005614156,0.001194973,0.006354447,0.2071987,0.04063348,0.008864284,0.732626],"study_design_scores_gemma":[0.0003620779,0.001042226,0.002866925,0.0004243714,0.000477363,0.002083303,0.0008107095,0.4121826,0.317479,0.07658633,0.1853397,0.0003452933],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006931703,0.0002042795,0.9671308,0.0003242691,0.0002205254,0.0001823715,0.000321082,0.01818542,0.006499634],"genre_scores_gemma":[0.1523823,0.0002384957,0.8296812,0.0003561088,0.0003005036,0.000428645,0.0008969845,0.003141831,0.01257391],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02400843,"threshold_uncertainty_score":0.08031619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04603330912543565,"score_gpt":0.3085922021437573,"score_spread":0.2625588930183216,"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."}}