{"id":"W4401047440","doi":"10.2139/ssrn.4907583","title":"Multi-Granularity Prosodic Speech Synthesis with Grammar Information","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Granularity; Computer science; Grammar; Natural language processing; Artificial intelligence; Speech recognition; Linguistics; Programming language","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":[0.0003584038,0.0007228657,0.0006754227,0.0004934149,0.0002755039,0.0007623988,0.0004492351,0.0006124288,0.006609267],"category_scores_gemma":[0.001112928,0.000525526,0.000524939,0.000454411,0.0002113791,0.0009430539,0.001391489,0.0009645586,0.001539518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001733688,"about_ca_system_score_gemma":0.0002992238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004969629,"about_ca_topic_score_gemma":0.001142433,"domain_scores_codex":[0.9997236,0.00006614703,0.00002240799,0.00009676022,0.00005938017,0.00003174563],"domain_scores_gemma":[0.9994294,0.000326535,0.00002823645,0.0001280889,0.00005741686,0.00003033327],"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":[0.001464647,0.0001282233,0.0006282926,0.0003307119,0.0001163729,0.0005154409,0.000221396,0.07195384,0.3514594,0.00993898,0.002350071,0.5608925],"study_design_scores_gemma":[0.0001470297,0.0002862015,0.001377419,0.00004651606,0.0001329403,0.0002480233,0.0001261718,0.8837206,0.09086779,0.01749435,0.005515234,0.00003780748],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03757618,0.0002954715,0.9545468,0.0001115759,0.0001146796,0.0000418165,0.0003040932,0.00303202,0.003977414],"genre_scores_gemma":[0.5697564,0.0002344282,0.4248724,0.00008790279,0.0001169216,0.0001024291,0.0007690786,0.0006978353,0.003362548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006609267,"threshold_uncertainty_score":0.02211016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007283251231385494,"score_gpt":0.2452220335663859,"score_spread":0.2379387823350005,"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."}}