{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001052174,0.001189791,0.0007895868,0.0007732836,0.0006378596,0.001016334,0.001011825,0.001846555,0.007447428],"category_scores_gemma":[0.004700623,0.0005945097,0.001038428,0.001202617,0.0004879997,0.001563687,0.001094081,0.001647498,0.005624262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000275793,"about_ca_system_score_gemma":0.0008490049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001441952,"about_ca_topic_score_gemma":0.002115335,"domain_scores_codex":[0.9994305,0.0001601012,0.00004898547,0.0002035052,0.0001121071,0.00004479356],"domain_scores_gemma":[0.9989512,0.0004890775,0.00006472386,0.0001576975,0.0002967943,0.00004040432],"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":[0.0006241585,0.0001559667,0.0007953639,0.00020474,0.0001542477,0.0001918711,0.0001460051,0.08807941,0.07523761,0.009647713,0.004805758,0.8199572],"study_design_scores_gemma":[0.00007546267,0.0001707733,0.0009964156,0.00003270253,0.00008571811,0.0003565903,0.0001055855,0.9047321,0.07089716,0.01046454,0.01203617,0.00004674113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004090573,0.00004867391,0.9941,0.00005397966,0.00007383529,0.00002950935,0.00004629356,0.0009597861,0.0005973086],"genre_scores_gemma":[0.04557836,0.0001160566,0.9501069,0.0001107992,0.00006088551,0.0001171211,0.0004496025,0.0004391577,0.00302107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007447428,"threshold_uncertainty_score":0.02491409,"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."}}