{"id":"W4372259784","doi":"10.1109/icassp49357.2023.10095515","title":"Grad-StyleSpeech: Any-Speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Speech recognition; Speech synthesis; Similarity (geometry); Speech processing; Generative grammar; Generative model; Artificial intelligence","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":[0.0004687746,0.0003312776,0.0003562252,0.0005958579,0.0002537225,0.0002663968,0.0009987116,0.00011855,0.0003494601],"category_scores_gemma":[0.0001102577,0.0002440763,0.0001323721,0.002145734,0.00006057602,0.0007070851,0.0004196232,0.0001603204,0.003825745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007121971,"about_ca_system_score_gemma":0.00007525466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009652114,"about_ca_topic_score_gemma":0.0001134735,"domain_scores_codex":[0.9972326,0.0001271344,0.0003100277,0.0008728429,0.0007997001,0.0006576953],"domain_scores_gemma":[0.9979371,0.0005328591,0.00007906363,0.0008708923,0.0002021169,0.0003779191],"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":[0.0001033392,0.0002760973,0.000195584,0.00001765112,0.0001031203,0.0004281145,0.0011169,0.0002949962,0.003224727,0.05775413,0.0188587,0.9176266],"study_design_scores_gemma":[0.001189541,0.0006020367,0.008932268,0.0003808842,0.0000771183,0.0003048591,0.001602213,0.8124199,0.1302924,0.02260199,0.01929575,0.002301042],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07757206,0.00001784032,0.8136438,0.007775473,0.0002595263,0.0007078444,0.00002298804,0.002685884,0.09731457],"genre_scores_gemma":[0.6731507,0.00006423508,0.3144497,0.001827406,0.0001011354,0.0002103027,0.000005103379,0.00006482421,0.01012666],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9153256,"threshold_uncertainty_score":0.9969499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04366180071214854,"score_gpt":0.2385083710509253,"score_spread":0.1948465703387767,"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."}}