{"id":"W2052003572","doi":"10.1007/s10772-005-2166-6","title":"Aligning Text and Phonemes for Speech Technology Applications Using an EM-Like Algorithm","year":2005,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Speech recognition; Speech synthesis; Speech technology; Algorithm; Artificial intelligence; Natural language processing","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":[0.0004292779,0.0001855907,0.0002998471,0.001961638,0.0001399245,0.0001616804,0.001635514,0.0002893265,0.00003686498],"category_scores_gemma":[0.000126276,0.0001811924,0.00009894162,0.0005850838,0.0001718271,0.0007152167,0.0002582124,0.0003172701,0.00001713392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001462465,"about_ca_system_score_gemma":0.000112317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005169385,"about_ca_topic_score_gemma":0.00001773483,"domain_scores_codex":[0.998351,0.00002254734,0.0006107537,0.0003506267,0.0003809905,0.0002840398],"domain_scores_gemma":[0.9979399,0.0001014191,0.0004985461,0.0003198386,0.001046948,0.00009332455],"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":[0.000007004208,0.0001231248,0.0001360287,0.000002531811,0.00009459504,0.00004689145,0.00005417845,0.000008216472,0.0124059,0.006416903,0.0001269178,0.9805777],"study_design_scores_gemma":[0.002828685,0.0005963357,0.0001355603,0.0001708955,0.00009478653,0.02013234,0.00174169,0.0802945,0.5306677,0.1432375,0.2193181,0.0007819496],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06907795,0.0005206947,0.9171021,0.0121286,0.0005038129,0.0002632325,0.00001648506,0.0002263269,0.0001607926],"genre_scores_gemma":[0.09716064,0.0001463933,0.9016714,0.0004046099,0.0004856705,0.00002697522,0.000002737946,0.00001941761,0.00008218711],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9797958,"threshold_uncertainty_score":0.7388811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02173062261395104,"score_gpt":0.3048551054452593,"score_spread":0.2831244828313083,"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."}}