{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007773428,0.0003463835,0.0005210258,0.0004037429,0.0006236124,0.000420675,0.0009886975,0.0001158948,0.0004753947],"category_scores_gemma":[0.0002887125,0.000352157,0.0001002948,0.0004490312,0.0002168363,0.000421047,0.0004801189,0.0005978709,0.000005541852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001433145,"about_ca_system_score_gemma":0.0003160367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004032718,"about_ca_topic_score_gemma":0.000008437909,"domain_scores_codex":[0.9969674,0.0001546307,0.0006810739,0.0008330672,0.0009502504,0.0004135715],"domain_scores_gemma":[0.9975572,0.0005546723,0.0005670912,0.0002834561,0.0008075549,0.0002300379],"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":[0.0008809923,0.0007123147,0.0005985901,0.0003119206,0.0002209614,0.00008678042,0.001298102,0.0002094104,0.236731,0.004796318,0.006305875,0.7478477],"study_design_scores_gemma":[0.001331668,0.0008682678,0.0001500018,0.0001114045,0.0000694652,0.0001226331,0.001902609,0.9682258,0.01889936,0.004030991,0.003771796,0.0005160128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1359567,0.0005758097,0.8463379,0.007157706,0.002295551,0.001408559,0.001519498,0.0003415402,0.004406833],"genre_scores_gemma":[0.9754838,0.00008396478,0.02238268,0.0006140259,0.0001484493,0.00008501425,0.00009757699,0.00003088861,0.001073607],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9680164,"threshold_uncertainty_score":0.9998931,"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."}}