{"id":"W1988809937","doi":"10.5539/mas.v4n10p97","title":"Concatenative Synthesis of Persian Language Based on Word, Diphone and Triphone Databases","year":2010,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech synthesis; Speech recognition; Word (group theory); Persian; Set (abstract data type); Vocabulary; Natural language processing; Artificial intelligence; Speech corpus; Part of speech; Database; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000322054,0.0006043775,0.0004407386,0.0003996178,0.0003378744,0.0004495151,0.0003667161,0.0002950412,0.003076835],"category_scores_gemma":[0.0005446806,0.0001638067,0.0003925861,0.0002739159,0.0002201766,0.000581229,0.0003621878,0.0002337058,0.001091075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001947245,"about_ca_system_score_gemma":0.0003027017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008933333,"about_ca_topic_score_gemma":0.001094174,"domain_scores_codex":[0.9997544,0.00005641107,0.00002634596,0.00007254641,0.00007319772,0.00001715864],"domain_scores_gemma":[0.9997883,0.00007678042,0.00001872479,0.00003011928,0.00007434699,0.00001170254],"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":[0.0009274947,0.00007867698,0.0009378667,0.0005175229,0.00009923826,0.0007598625,0.0003785076,0.04167377,0.3474612,0.007838232,0.002512857,0.5968148],"study_design_scores_gemma":[0.0001376249,0.000780879,0.001940339,0.00005417243,0.0002379791,0.001660894,0.0002678094,0.5133974,0.4440449,0.005519249,0.03189137,0.00006736847],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07197268,0.001198619,0.9156928,0.0001189095,0.0002218858,0.0001198384,0.000267654,0.003961204,0.006446388],"genre_scores_gemma":[0.500062,0.0006678139,0.490868,0.0001106826,0.000111094,0.0001962926,0.0007849804,0.0001895298,0.007009468],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003076835,"threshold_uncertainty_score":0.01029301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01549304779278035,"score_gpt":0.2480546913990974,"score_spread":0.232561643606317,"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."}}