{"id":"W1512994456","doi":"10.1023/a:1015568521453","title":"Learning Prosodic Patterns for Mandarin Speech Synthesis","year":2002,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; University of Alberta","funders":"Chinese Academy of Sciences","keywords":"Naturalness; Computer science; Prosody; Intelligibility (philosophy); Speech synthesis; Speech recognition; Cluster analysis; Artificial intelligence; Decision tree; Artificial neural network; 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":[0.0004791535,0.0005170045,0.0004451274,0.0004829282,0.0002355177,0.0003950749,0.0004744842,0.0004821911,0.003075183],"category_scores_gemma":[0.001672475,0.000433442,0.0003849708,0.0004140539,0.0001687229,0.0005775858,0.0006250506,0.0007598375,0.0007232505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001956131,"about_ca_system_score_gemma":0.0003518865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00155012,"about_ca_topic_score_gemma":0.003006499,"domain_scores_codex":[0.9998108,0.00005501442,0.00001423111,0.00006883206,0.00002994578,0.00002129479],"domain_scores_gemma":[0.9995546,0.0002522233,0.00002761558,0.00004859032,0.00009118613,0.000025743],"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":[0.0004099193,0.0001042488,0.001310816,0.00007840311,0.00005006065,0.00007594562,0.00007593635,0.03413103,0.03088453,0.001002232,0.001444092,0.9304327],"study_design_scores_gemma":[0.00007902429,0.0002228839,0.002334846,0.00001770888,0.00006279707,0.00007787797,0.00008042553,0.9727631,0.01847449,0.004471454,0.001400146,0.00001518269],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1737383,0.0007835721,0.8190946,0.0001656242,0.0001033934,0.00009592728,0.0003787675,0.002293221,0.003346693],"genre_scores_gemma":[0.6167891,0.0004807817,0.3776247,0.00008182262,0.00006033072,0.0001615584,0.0009329877,0.0002087345,0.003659929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003075183,"threshold_uncertainty_score":0.01028752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03588713324134827,"score_gpt":0.2437557515907929,"score_spread":0.2078686183494446,"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."}}