{"id":"W6939194750","doi":"10.60692/38hgp-2s302","title":"Synthetic Speech Dataset","year":2019,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Speech synthesis; Speech processing; Spoken language; Natural language; Speech corpus; Speech technology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003644127,0.0001324855,0.0001693244,0.0002400123,0.00006922014,0.000399121,0.00057177,0.00006885886,0.0002074875],"category_scores_gemma":[0.00001644388,0.0001082799,0.00005573158,0.0002483355,0.00001090195,0.001574839,0.000125434,0.00006533651,0.03931185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005494758,"about_ca_system_score_gemma":0.00002625876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003357848,"about_ca_topic_score_gemma":4.129997e-8,"domain_scores_codex":[0.9988129,0.00005515537,0.0003877636,0.000184723,0.0003443149,0.000215204],"domain_scores_gemma":[0.9988049,0.00001315647,0.0001685783,0.0008373242,0.00008742597,0.00008861334],"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":[0.0002123481,0.0000532951,0.2206823,0.004161691,0.0005824093,0.0001902178,0.18498,0.0002265619,0.00009264946,0.06654487,0.05258651,0.4696872],"study_design_scores_gemma":[0.009707636,0.0005247116,0.0940368,0.001929597,0.0001477999,0.00452127,0.0377349,0.5111521,0.05316285,0.0001070494,0.2818578,0.005117473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3721812,0.000003446728,0.5128656,0.0004209024,0.00291313,0.001224434,0.001247003,0.001524957,0.1076193],"genre_scores_gemma":[0.9916496,4.923004e-8,0.007556894,0.0004466674,0.00002732372,0.00001948931,0.00006562238,0.000004777918,0.0002295225],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6194685,"threshold_uncertainty_score":0.9614362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03117079637534485,"score_gpt":0.2093747215776078,"score_spread":0.178203925202263,"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."}}