{"id":"W3162841994","doi":"10.18653/v1/2021.findings-acl.312","title":"Learning Robust Latent Representations for Controllable Speech Synthesis","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vanguard College","funders":"","keywords":"Computer science; Transformer; Speech recognition; Latent variable; Artificial intelligence; Encoder; Probabilistic latent semantic analysis; Mutual information; Pattern recognition (psychology)","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":[0.0008799914,0.0008407067,0.000686403,0.0003823564,0.0002223398,0.0007181383,0.0009546817,0.0007128884,0.002518993],"category_scores_gemma":[0.003082902,0.0005611061,0.0008524818,0.0004149808,0.0007758873,0.001452743,0.00165244,0.001831066,0.0008313155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005845783,"about_ca_system_score_gemma":0.000672926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001811735,"about_ca_topic_score_gemma":0.003224855,"domain_scores_codex":[0.9994605,0.0001844972,0.00003138625,0.0001700066,0.0001010815,0.0000526035],"domain_scores_gemma":[0.9990854,0.0005501752,0.00007150866,0.0001634201,0.00009156089,0.00003792476],"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":[0.0002651858,0.0001074216,0.0006173156,0.0001736249,0.0001230822,0.0001175097,0.000167572,0.6863913,0.05033157,0.04407933,0.002762001,0.2148642],"study_design_scores_gemma":[0.000006191484,0.0000147665,0.00004646019,0.000003757711,0.000004870345,0.00001019574,0.000006020913,0.9879583,0.004139177,0.007475026,0.0003304699,0.000004674264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01344677,0.000146623,0.984741,0.0000838122,0.00002076524,0.00001558068,0.0001302439,0.0008311153,0.0005841333],"genre_scores_gemma":[0.668323,0.0003409895,0.3243603,0.0001841761,0.00006947993,0.0002092396,0.001391292,0.0005583658,0.004563155],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002518993,"threshold_uncertainty_score":0.008426845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05897369964401934,"score_gpt":0.2807863436266693,"score_spread":0.2218126439826499,"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."}}