{"id":"W2901025079","doi":"10.1109/icassp.2019.8682880","title":"Representation Mixing for TTS Synthesis","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Pronunciation; Character (mathematics); Mixing (physics); Representation (politics); Speech synthesis; Software deployment; Speech recognition; Parametric statistics; Inference; Artificial intelligence; Natural language processing; Encoder; Control (management); Linguistics; Mathematics","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":[0.0006311926,0.0007171169,0.0004224702,0.0005267527,0.000356808,0.001112732,0.0006002082,0.0009069255,0.008142397],"category_scores_gemma":[0.002402777,0.0003381946,0.0006761769,0.0005605491,0.0005187322,0.001337691,0.001371939,0.001467489,0.003324464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005352647,"about_ca_system_score_gemma":0.0005076893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009895033,"about_ca_topic_score_gemma":0.001208403,"domain_scores_codex":[0.999431,0.0001479094,0.00004834812,0.0001567364,0.0001684067,0.00004754116],"domain_scores_gemma":[0.9995061,0.0002135725,0.00003448374,0.0001295622,0.00008279236,0.00003355699],"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":[0.0004634512,0.00009610729,0.0004451557,0.0002472778,0.00008381156,0.000208881,0.000174479,0.1371446,0.1599761,0.069792,0.00502733,0.6263407],"study_design_scores_gemma":[0.00002599066,0.00009874802,0.0001765556,0.00003413457,0.00002921378,0.0001797993,0.00002678109,0.8569558,0.07521423,0.04992346,0.01730484,0.00003031374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004203159,0.000201014,0.9917684,0.0000958088,0.00006037447,0.0000211244,0.00009657138,0.001650645,0.001902872],"genre_scores_gemma":[0.4139329,0.0005031354,0.5720714,0.000243747,0.0001895755,0.0001773291,0.001122197,0.0009282185,0.0108316],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008142397,"threshold_uncertainty_score":0.02723897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07700848133495143,"score_gpt":0.313404557081405,"score_spread":0.2363960757464535,"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."}}