{"id":"W1990505856","doi":"10.1109/icassp.2014.6854321","title":"Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Naturalness; Parametric statistics; Computer science; Speech synthesis; Artificial neural network; Speech recognition; Probability density function; Layer (electronics); Deep neural networks; Mixture model; Statistical model; Artificial intelligence; Mathematics; Statistics","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":[0.0007314714,0.0001549413,0.0002744335,0.0002420541,0.00009033376,0.0001473861,0.0004327386,0.0001400365,0.00007527889],"category_scores_gemma":[0.002133135,0.0001355934,0.0000733651,0.0005271453,0.00002239161,0.0001614807,0.00008196736,0.0001459015,0.00004502795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004849803,"about_ca_system_score_gemma":0.00002388021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005618233,"about_ca_topic_score_gemma":0.0002267961,"domain_scores_codex":[0.9985265,0.0001243893,0.0002872464,0.0004450915,0.0002173098,0.0003995242],"domain_scores_gemma":[0.9964512,0.00290771,0.00004348454,0.0003533176,0.0001081201,0.0001361437],"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":[0.00002051609,0.0001125682,0.0003334563,0.0000248102,0.00001531195,0.00001522267,0.00002834406,0.03919595,0.00003565282,0.0129351,0.0004418647,0.9468412],"study_design_scores_gemma":[0.0001651063,0.00002595943,0.0003223513,0.00001564509,0.00001466631,0.00001530615,0.00001500349,0.9892396,0.0004348662,0.009512761,0.00004618543,0.0001925747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007316679,0.00002007109,0.9907631,0.000228796,0.0001888536,0.0002156126,0.000001667702,0.0001354295,0.001129747],"genre_scores_gemma":[0.5902571,0.000007613695,0.4092905,0.0003301768,0.00004963795,0.00002869945,0.000001591946,0.000007601499,0.0000270766],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9500436,"threshold_uncertainty_score":0.5529337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02765918503457674,"score_gpt":0.2498129052068847,"score_spread":0.222153720172308,"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."}}