{"id":"W2024218073","doi":"10.1145/1066078.1066081","title":"A speech synthesizer for Persian text using a neural network with a smooth ergodic HMM","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Preprocessor; Speech recognition; Speech synthesis; Hidden Markov model; Artificial neural network; Intelligibility (philosophy); Natural language processing; Artificial intelligence; Active listening; Language model; Time delay neural network","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":[0.0002510062,0.0002329326,0.0002020924,0.0003323086,0.0006035449,0.0005964686,0.0005390585,0.0001028038,0.0001406461],"category_scores_gemma":[0.00005832271,0.0002010975,0.0001155034,0.0006760423,0.00004985222,0.003724453,0.00000919282,0.0002051287,0.00006414239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001266672,"about_ca_system_score_gemma":0.0001527359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001302027,"about_ca_topic_score_gemma":0.00004445101,"domain_scores_codex":[0.9985703,0.00004005507,0.0003847983,0.0002428687,0.0003417632,0.0004202345],"domain_scores_gemma":[0.9989516,0.0001020082,0.0002125881,0.0004548551,0.0001449832,0.0001339912],"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":[0.0000513798,0.00004333752,0.000002657861,0.00004908973,0.00001837175,0.000003685921,0.004878422,0.004076049,0.00004718399,0.00006096145,0.00003073988,0.9907381],"study_design_scores_gemma":[0.001687179,0.0002139163,0.0001941792,0.0004691613,0.0001046727,0.0005417122,0.007811497,0.9742826,0.005775776,0.0002508177,0.007864279,0.000804249],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01013616,0.00005112241,0.9830914,0.002909842,0.00008829872,0.0004252736,0.00001262115,0.0003696737,0.002915606],"genre_scores_gemma":[0.5533249,0.000001867766,0.444677,0.001759896,0.00008511516,0.00005446177,0.000005640035,0.00001568876,0.00007540989],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9899338,"threshold_uncertainty_score":0.820052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01561256109669238,"score_gpt":0.2520033667490014,"score_spread":0.236390805652309,"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."}}