{"id":"W3175990969","doi":"10.21428/594757db.930ce165","title":"Learning to Model Prosodic and Spectral Features for Non-parallel Emotive Speech Conversion","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Dalhousie University","funders":"Vector Institute; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Emotive; Computer science; Speech recognition; Generative grammar; Speech synthesis; Artificial neural network; Convolutional neural network; Kernel (algebra); Artificial intelligence; Speech enhancement","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005450488,0.0008646544,0.0003365812,0.0002770841,0.0001433986,0.0002979443,0.000572998,0.000433957,0.001461461],"category_scores_gemma":[0.001139648,0.0003142498,0.0005527394,0.0001983608,0.0003573556,0.0006072336,0.0006061086,0.001077866,0.0005124728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002871825,"about_ca_system_score_gemma":0.0003091534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001706786,"about_ca_topic_score_gemma":0.00311761,"domain_scores_codex":[0.9998226,0.00004759073,0.000006866847,0.0000666207,0.00003294022,0.0000234388],"domain_scores_gemma":[0.9997064,0.0001550645,0.00002996188,0.0000428565,0.0000514071,0.00001428948],"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":[0.0002224458,0.0001857711,0.001653707,0.00008540278,0.0001252238,0.0001601909,0.00009674377,0.668054,0.05320303,0.005828173,0.00200139,0.2683839],"study_design_scores_gemma":[0.000002097723,0.00002096351,0.0002324559,0.00000239896,0.000007867844,0.00001993221,0.000003950816,0.9950827,0.003247674,0.00104036,0.000335407,0.000004132223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03915721,0.0002570397,0.9581244,0.0001083348,0.00005913131,0.00004388478,0.00008051121,0.000571824,0.001597574],"genre_scores_gemma":[0.8243012,0.0004242108,0.1678273,0.0002198297,0.00006198945,0.0001540777,0.0005520814,0.000179682,0.006279587],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001706786,"threshold_uncertainty_score":0.004889011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0176946675514212,"score_gpt":0.2511454037525856,"score_spread":0.2334507362011644,"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."}}