{"id":"W2963912924","doi":"","title":"Sample-efficient adaptive text-to-speech","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Naturalness; Speech recognition; Artificial neural network; Embedding; Benchmark (surveying); Similarity (geometry); Stochastic gradient descent; Speaker recognition; Mean opinion score; Gradient descent; Artificial intelligence; Sample (material); Speaker diarisation; Metric (unit)","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":[0.0001837591,0.0001452691,0.0001391592,0.0002484679,0.0002212134,0.0000678203,0.0008840011,0.00006400372,0.0003829797],"category_scores_gemma":[0.0001034229,0.0001547618,0.00009049436,0.001179018,0.0001092278,0.0002064594,0.0003019164,0.0000883965,0.003068619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000100675,"about_ca_system_score_gemma":0.00005706669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008425512,"about_ca_topic_score_gemma":0.00003236833,"domain_scores_codex":[0.9987686,0.00007494458,0.0001072114,0.0006174681,0.00009815975,0.000333597],"domain_scores_gemma":[0.9987102,0.000195978,0.00005537545,0.0005720817,0.000220372,0.0002459709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008527226,0.0002642953,0.0008767027,0.000004327163,0.00005923045,0.0002608108,0.0006447887,0.00119755,0.0004776643,0.908201,0.002772645,0.0851557],"study_design_scores_gemma":[0.0005986568,0.0003710144,0.003404351,0.00003286824,0.00002465009,0.00002235397,0.0002979734,0.956036,0.01074532,0.01241503,0.01548792,0.0005638477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1514402,0.000002776255,0.8293669,0.0001647933,0.0002367594,0.0001299065,0.000007342022,0.0002112161,0.01844019],"genre_scores_gemma":[0.9669608,0.000003359874,0.03114997,0.0005829367,0.00007892779,4.930852e-7,7.836389e-7,0.000008245101,0.001214509],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9548385,"threshold_uncertainty_score":0.9977076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08424185677777325,"score_gpt":0.1921571094293518,"score_spread":0.1079152526515785,"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."}}