{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037011,0.0001876749,0.000328751,0.0001918046,0.00006683753,0.0003536803,0.0009206798,0.0002096832,0.0001974126],"category_scores_gemma":[0.0005332683,0.0001751751,0.0002852292,0.0001249179,0.00001214043,0.0002015192,0.0006063975,0.0001400824,0.0003275975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005177818,"about_ca_system_score_gemma":0.00009544021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003796088,"about_ca_topic_score_gemma":0.000008242775,"domain_scores_codex":[0.998436,0.00007882812,0.000287942,0.0007243755,0.0002509643,0.0002218716],"domain_scores_gemma":[0.9975656,0.001065948,0.0001731513,0.0009664724,0.0001638983,0.00006487469],"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":[0.00001263696,0.00007726521,0.0002487145,0.0002505639,0.0001320398,0.000005158329,0.0002766996,0.0002068819,0.0004744358,0.01227869,0.01857957,0.9674574],"study_design_scores_gemma":[0.0004977593,0.00004632738,0.002051078,0.0005220086,0.0001203791,0.00002245833,0.0002161385,0.6427686,0.2595382,0.08047471,0.01232288,0.001419489],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001649026,0.00004230573,0.9569735,0.001524896,0.00146131,0.0006941942,0.00001559208,0.0003460407,0.03729317],"genre_scores_gemma":[0.1471564,0.00006261326,0.8454131,0.0007044469,0.0002536518,0.0006318567,0.0000244567,0.00003204658,0.005721475],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9660379,"threshold_uncertainty_score":0.7143431,"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."}}