{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003172174,0.0001179917,0.0001220887,0.0001793662,0.0002691715,0.0002213015,0.0003369691,0.00004687149,0.000008134726],"category_scores_gemma":[0.00002163889,0.0001147741,0.00008121091,0.0004457517,0.00002603801,0.000501393,0.00003512994,0.00008460719,0.0002486921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003113027,"about_ca_system_score_gemma":0.00004622604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004618339,"about_ca_topic_score_gemma":3.458553e-7,"domain_scores_codex":[0.9988928,0.00002626754,0.0001707367,0.000345546,0.0002481181,0.0003164838],"domain_scores_gemma":[0.9995143,0.0001264104,0.00006119779,0.0001383664,0.00008729209,0.00007240861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003602529,0.000038359,0.00002287277,0.000303874,0.00003079142,0.00008219927,0.001046871,0.01553394,0.1917007,0.0001111947,0.02751358,0.7635796],"study_design_scores_gemma":[0.0002358388,0.00001464953,0.000006099074,0.00006697581,0.000006470396,0.00001425777,0.00003644538,0.973832,0.0237127,0.0005686511,0.001335268,0.0001706364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05980299,0.00001922065,0.933506,0.005571658,0.0003018193,0.0001254783,0.000002413588,0.0005231567,0.0001472578],"genre_scores_gemma":[0.9466329,0.000003850022,0.04690071,0.00602193,0.0002461676,0.00004084858,0.000005216314,0.00002029429,0.0001280593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9582981,"threshold_uncertainty_score":0.468035,"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."}}