{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006276478,0.0003733755,0.0005041001,0.0002537305,0.0005293528,0.0008021467,0.0006854188,0.0002397522,0.002364374],"category_scores_gemma":[0.0002447081,0.0003371536,0.0001170975,0.0006860971,0.0001801324,0.000768859,0.0003937819,0.0002210325,0.0004718126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008236766,"about_ca_system_score_gemma":0.0003298044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002204505,"about_ca_topic_score_gemma":0.00001658781,"domain_scores_codex":[0.9969595,0.0002566046,0.0006609926,0.001045404,0.000539444,0.0005380653],"domain_scores_gemma":[0.9981093,0.0004760983,0.0001956102,0.0005001984,0.0004681261,0.0002506398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002062797,0.0007535628,0.007805071,0.0003064632,0.0003595832,0.00002371091,0.0003437476,0.000002947846,0.01655809,0.06783557,0.557828,0.347977],"study_design_scores_gemma":[0.01276825,0.0009514765,0.01168622,0.0014244,0.0003558056,0.0001151025,0.001833158,0.3655627,0.201804,0.016598,0.3844858,0.002415046],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2074764,0.003934597,0.3131786,0.05976866,0.003981939,0.00256143,0.0001814172,0.0006478281,0.4082691],"genre_scores_gemma":[0.8442907,0.001059488,0.02154987,0.006551101,0.0001090281,0.00006810969,0.00002681644,0.00001613586,0.1263288],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6368143,"threshold_uncertainty_score":0.999908,"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."}}