{"id":"W4408353590","doi":"10.1109/icassp49660.2025.10890553","title":"Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Prosody; Speech synthesis; Speech recognition; Computer science","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":[0.0009874043,0.001015438,0.0007073777,0.0005616216,0.0003449025,0.0007700602,0.00119249,0.0007755503,0.006010918],"category_scores_gemma":[0.002083952,0.0003167508,0.0007327275,0.0005292973,0.0005235775,0.000961163,0.001596295,0.000994921,0.004086486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002832262,"about_ca_system_score_gemma":0.0006146814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001417256,"about_ca_topic_score_gemma":0.002411668,"domain_scores_codex":[0.9993997,0.0001225043,0.0000359872,0.0001923769,0.0002073733,0.00004211336],"domain_scores_gemma":[0.9993692,0.0002302543,0.00004616796,0.00013788,0.0001691944,0.00004734093],"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":[0.001060983,0.0001527727,0.0009635761,0.0002486869,0.0001258858,0.0002710341,0.0002100734,0.04939634,0.1933189,0.005648526,0.01074607,0.7378572],"study_design_scores_gemma":[0.00009828322,0.0003884675,0.00135781,0.00002871619,0.00006284477,0.0004821784,0.00007939227,0.8353816,0.1338441,0.006702139,0.0214999,0.0000745884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01218769,0.0003041052,0.9782009,0.00009644606,0.0001927208,0.00008810916,0.0004392688,0.006083705,0.002406999],"genre_scores_gemma":[0.2802838,0.0004923806,0.700816,0.0003438176,0.0002457957,0.0003580669,0.003592457,0.001707236,0.01216048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006010918,"threshold_uncertainty_score":0.02010852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02149870901442346,"score_gpt":0.2517910556442048,"score_spread":0.2302923466297814,"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."}}