{"id":"W4288107168","doi":"10.48550/arxiv.1909.06805","title":"Many-to-Many Voice Conversion using Cycle-Consistent Variational\\n Autoencoder with Multiple Decoders","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Autoencoder; Computer science; Speech recognition; Path (computing); Task (project management); Consistency (knowledge bases); Artificial intelligence; Deep learning; Engineering","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":[0.0002775975,0.0004115434,0.0004279761,0.0005191393,0.000245819,0.0002050367,0.001341647,0.0002965698,0.000135305],"category_scores_gemma":[0.00006812118,0.0004409945,0.0002394446,0.0005955315,0.00007821348,0.0004956879,0.001246193,0.0004228959,0.000753788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004859152,"about_ca_system_score_gemma":0.0004308389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000366298,"about_ca_topic_score_gemma":0.00006255215,"domain_scores_codex":[0.9974419,0.000181797,0.0002578089,0.001425144,0.000248837,0.000444509],"domain_scores_gemma":[0.9974809,0.0003465035,0.0003233624,0.001180064,0.0003702662,0.0002989435],"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":[0.0001312989,0.0002077035,0.01303571,0.000122103,0.000335067,0.0003299031,0.0004152853,0.9698077,0.00009207439,0.01433466,0.0003623535,0.0008261558],"study_design_scores_gemma":[0.000839537,0.00004562752,0.005182798,0.0001829044,0.0001213043,0.00001999372,0.0001335909,0.990334,0.0002113381,0.001675131,0.0006397727,0.0006140269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1726149,0.000009658523,0.8238003,0.0001988327,0.0006587286,0.0005054959,0.00002691865,0.0002313128,0.001953842],"genre_scores_gemma":[0.8964255,0.00002129344,0.1017555,0.0005908306,0.00004868803,0.000001731065,0.00001930975,0.00003005656,0.001107079],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7238107,"threshold_uncertainty_score":0.9998042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07116699081042,"score_gpt":0.1941445700142372,"score_spread":0.1229775792038172,"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."}}