{"id":"W4415540898","doi":"10.1145/3746027.3754745","title":"Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"National Natural Science Foundation of China","keywords":"Autoregressive model; Language model; Set (abstract data type); Inference; Codec; Face (sociological concept); Speech processing; Speech synthesis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007124827,0.0008040779,0.0005623038,0.0004629435,0.0002711205,0.0006175387,0.00129088,0.0007040405,0.004240506],"category_scores_gemma":[0.002593536,0.000383597,0.0006622842,0.0004058122,0.0003607114,0.001001197,0.0007822511,0.001527247,0.002863776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004678023,"about_ca_system_score_gemma":0.0009970195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006110212,"about_ca_topic_score_gemma":0.00963534,"domain_scores_codex":[0.9995247,0.0001124446,0.00003117824,0.0001204475,0.0001678137,0.00004341337],"domain_scores_gemma":[0.9991233,0.0004424916,0.00005241532,0.00009691335,0.0002543387,0.00003063885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004408282,0.0001549043,0.0006718293,0.0002400987,0.0001024371,0.0002700035,0.0001797691,0.3982066,0.05149132,0.0133662,0.008435472,0.5264406],"study_design_scores_gemma":[0.000008703718,0.00002906806,0.0000782229,0.000007120425,0.000008569874,0.00003450953,0.00000788048,0.9906143,0.006056868,0.001687656,0.001458316,0.000008663024],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008136044,0.0003325462,0.9857886,0.0001004714,0.00008162457,0.00004063741,0.0002402069,0.004051977,0.001227885],"genre_scores_gemma":[0.3888876,0.0005873837,0.5960568,0.0003555709,0.0001205055,0.000397641,0.002633689,0.001184184,0.009776783],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006110212,"threshold_uncertainty_score":0.01418591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03375509139618933,"score_gpt":0.2939912735728801,"score_spread":0.2602361821766908,"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."}}