{"id":"W3210530853","doi":"10.1109/icassp43922.2022.9746484","title":"A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Speech recognition","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":[0.001209038,0.0004504875,0.000471233,0.0005503509,0.0001629992,0.0009296467,0.0005874094,0.0005066113,0.003431899],"category_scores_gemma":[0.003803303,0.0001418551,0.0003926553,0.0003563632,0.0004863539,0.00114959,0.0008019529,0.0008565289,0.0007035811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002974666,"about_ca_system_score_gemma":0.0003003388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005619076,"about_ca_topic_score_gemma":0.0006469668,"domain_scores_codex":[0.9993349,0.000222741,0.0000509356,0.0001270294,0.000207047,0.00005732515],"domain_scores_gemma":[0.9986725,0.0007691892,0.00006103824,0.0002040906,0.0002080747,0.00008510458],"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":[0.002142006,0.0004010283,0.001475763,0.0002943662,0.00009428184,0.0001408914,0.0001400475,0.1048531,0.08213743,0.00556331,0.0009909287,0.8017669],"study_design_scores_gemma":[0.0001064038,0.001197722,0.003214845,0.00003844069,0.00007135707,0.0001981574,0.000116817,0.9131969,0.07586293,0.003846366,0.002107978,0.00004210866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4926011,0.002761368,0.4896672,0.000439414,0.0003062563,0.0001305278,0.0001777188,0.002763826,0.01115261],"genre_scores_gemma":[0.9221697,0.0002942843,0.07466713,0.0001168072,0.00004151417,0.00005273872,0.0002050524,0.0001183467,0.002334418],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003431899,"threshold_uncertainty_score":0.01148081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07575626700609553,"score_gpt":0.3305673919311458,"score_spread":0.2548111249250503,"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."}}