{"id":"W2151120341","doi":"","title":"Automatic Syllabification with Structured SVMs for Letter-to-Phoneme Conversion","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Syllabification; Computer science; Discriminative model; Artificial intelligence; Word error rate; Speech recognition; Natural language processing; German; Syllable; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007900781,0.00008694246,0.0001022588,0.00009606023,0.000140426,0.00004579577,0.0002848321,0.00003692081,0.000215142],"category_scores_gemma":[0.00002991704,0.0000640589,0.00003335048,0.0002323717,0.00002296204,0.0001971857,0.00002654798,0.00003154771,0.0001920826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002630662,"about_ca_system_score_gemma":0.00003206986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008577274,"about_ca_topic_score_gemma":0.000005513188,"domain_scores_codex":[0.9992802,0.00002138055,0.0001232919,0.0002444618,0.0001819194,0.0001487446],"domain_scores_gemma":[0.9993955,0.00008728313,0.00004482452,0.0002955624,0.0000942599,0.00008254835],"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":[0.00008702122,0.0002275061,0.001299198,0.0001421375,0.0001051945,0.000044299,0.003614974,0.00004297474,0.04712929,0.01234321,0.2393653,0.6955989],"study_design_scores_gemma":[0.002774629,0.0006415426,0.03699117,0.00007403331,0.00002982617,0.0002942038,0.00017074,0.3893781,0.508922,0.001708663,0.05799192,0.001023199],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1773586,0.000002726578,0.8176207,0.002984011,0.0001565115,0.0003766996,0.000002141112,0.0002874038,0.001211236],"genre_scores_gemma":[0.5381365,0.000001255791,0.4583394,0.002741073,0.00004367272,0.00003743115,0.000003897901,0.000006352425,0.0006904798],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6945757,"threshold_uncertainty_score":0.2612246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02431177596683813,"score_gpt":0.2251428728970672,"score_spread":0.2008310969302291,"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."}}