{"id":"W4386609311","doi":"10.1109/lsp.2023.3313515","title":"Rhythm Modeling for Voice Conversion","year":2023,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Speech recognition; Rhythm; Computer science; Prosody; Speech processing; Artificial intelligence; Pattern recognition (psychology); Acoustics","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":[0.0003307324,0.0005695153,0.0004210273,0.0003921457,0.0002361935,0.0006582456,0.0007331228,0.0004555254,0.00203297],"category_scores_gemma":[0.00136032,0.0002301635,0.0007923779,0.0003816723,0.0002632353,0.0005668965,0.000488943,0.0009871926,0.001185247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003363357,"about_ca_system_score_gemma":0.0004303329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003264722,"about_ca_topic_score_gemma":0.003745758,"domain_scores_codex":[0.9997807,0.00005858201,0.00001073168,0.00006692898,0.00006192086,0.00002103513],"domain_scores_gemma":[0.9997556,0.0000994436,0.00002817265,0.00004079421,0.0000624683,0.00001362843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001410235,0.0001192359,0.001671601,0.0001449165,0.0001299889,0.0001379207,0.0001173686,0.6925845,0.03632232,0.01775081,0.00566585,0.2452145],"study_design_scores_gemma":[0.000004986108,0.0000187478,0.0004557717,0.00000840382,0.000008883606,0.00004248328,0.0000100042,0.9894595,0.002045501,0.005143219,0.002793459,0.000009006256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01103864,0.0005185469,0.9844564,0.0001098215,0.00008790238,0.00003153982,0.000224284,0.0008502522,0.002682614],"genre_scores_gemma":[0.7127435,0.001888068,0.2694748,0.000280962,0.0004022423,0.0002593233,0.002315681,0.0007732774,0.01186214],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003264722,"threshold_uncertainty_score":0.00680095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04954250797524673,"score_gpt":0.2673340634600034,"score_spread":0.2177915554847566,"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."}}