{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002747228,0.0004037628,0.0002663138,0.0004065737,0.0001767544,0.0007381021,0.0002956846,0.000499155,0.005724018],"category_scores_gemma":[0.0007570224,0.0002136666,0.0002594572,0.0003702138,0.0002604808,0.0007969034,0.0005004561,0.0005409889,0.001637008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007432829,"about_ca_system_score_gemma":0.0001013336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001991155,"about_ca_topic_score_gemma":0.0004729764,"domain_scores_codex":[0.9998406,0.00002967534,0.000008636173,0.00003079412,0.00007318555,0.00001707855],"domain_scores_gemma":[0.999693,0.0001480007,0.00001419023,0.00004566533,0.00008373714,0.00001533757],"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":[0.0006862713,0.00009723683,0.0008908826,0.0002192094,0.0000436453,0.0003175203,0.00008664578,0.003840104,0.6761981,0.002078817,0.001066446,0.3144751],"study_design_scores_gemma":[0.0001633942,0.0005419866,0.008951922,0.00009498622,0.0001899727,0.001454536,0.0002397867,0.1246548,0.8438267,0.003546625,0.0162532,0.00008213554],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2024489,0.001245361,0.7745383,0.0002471957,0.0002495616,0.0001106083,0.0003231117,0.002441426,0.01839566],"genre_scores_gemma":[0.7229268,0.0009326838,0.2642644,0.0001598206,0.0001895186,0.00007009051,0.0006389161,0.0004203193,0.01039744],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005724018,"threshold_uncertainty_score":0.01914871,"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."}}