{"id":"W7148307382","doi":"10.1109/asru65441.2025.11434672","title":"Maestro-EVC: Controllable Emotional Voice Conversion Guided by References and Explicit Prosody","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Research Foundation","keywords":"Prosody; Representation (politics); Identity (music); Emotional prosody; Style (visual arts); Dynamics (music)","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":[0.0004055032,0.0005518461,0.0003368317,0.0002210481,0.0002157654,0.0005896076,0.0007793984,0.0004797569,0.002787913],"category_scores_gemma":[0.0009924094,0.00017736,0.0003106025,0.0001115677,0.0005157671,0.0005393701,0.001161767,0.0006657499,0.0008363349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001488193,"about_ca_system_score_gemma":0.0002062456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000384793,"about_ca_topic_score_gemma":0.0007365749,"domain_scores_codex":[0.9997203,0.00006080378,0.00001412381,0.00007907546,0.00009948097,0.00002613084],"domain_scores_gemma":[0.9997485,0.0001122087,0.00001997975,0.00005970117,0.00003929097,0.00002020741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004449145,0.0001233833,0.0006136469,0.0002838585,0.00007149032,0.0005052108,0.000390865,0.04986666,0.6022226,0.02553371,0.003972554,0.3159712],"study_design_scores_gemma":[0.00007401079,0.0003375825,0.0008205121,0.00004498928,0.00004436221,0.0006351707,0.00009820679,0.7050901,0.2557274,0.009794715,0.02726073,0.00007218885],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03203757,0.0004573182,0.9578109,0.00009495452,0.0001341945,0.00007349969,0.00009255732,0.002059435,0.007239615],"genre_scores_gemma":[0.7109067,0.0003507425,0.275867,0.0002623151,0.00008144189,0.000222462,0.0004229901,0.0006661515,0.01122008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002787913,"threshold_uncertainty_score":0.009326518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02420264739188317,"score_gpt":0.261497733206097,"score_spread":0.2372950858142139,"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."}}