{"id":"W2179428711","doi":"10.1007/s11042-015-3039-x","title":"High quality voice conversion using prosodic and high-resolution spectral features","year":2015,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"BC Research (Canada)","funders":"","keywords":"Timbre; Autoencoder; Feature (linguistics); Focus (optics); Artificial neural network; Quality (philosophy); Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0002352788,0.0001012326,0.0001299475,0.00005244311,0.0001868389,0.0001790054,0.0001515825,0.0000688293,0.00000822957],"category_scores_gemma":[0.00006512628,0.00009122703,0.0000215674,0.0001691629,0.00009315088,0.0003418182,0.00008834324,0.0000871314,0.00003331139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003477063,"about_ca_system_score_gemma":0.00004236181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003620975,"about_ca_topic_score_gemma":0.00001834442,"domain_scores_codex":[0.9991518,0.00005455205,0.0001568928,0.000310751,0.0001705941,0.0001553806],"domain_scores_gemma":[0.9992853,0.0001436549,0.00007656503,0.0002251959,0.0000864566,0.0001827692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003789711,0.0003111716,0.003565988,0.00007374387,0.00004189743,0.00000504024,0.001228628,0.00004584847,0.02294582,0.06472065,0.002321626,0.9047017],"study_design_scores_gemma":[0.006609545,0.0002643812,0.5289638,0.000121162,0.0001651424,0.0002063161,0.001169833,0.2865804,0.08803505,0.04767155,0.03821355,0.001999316],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4570625,0.0004518735,0.5375789,0.002584652,0.0002384881,0.0009771924,0.00009871578,0.0002776803,0.0007299341],"genre_scores_gemma":[0.7298723,0.00005522545,0.2694587,0.0002020734,0.0001756019,0.0000873,0.00003355914,0.000006597837,0.0001086392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9027024,"threshold_uncertainty_score":0.372013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07011119276320464,"score_gpt":0.2973966872773827,"score_spread":0.227285494514178,"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."}}