{"id":"W7083511276","doi":"","title":"Selective Classifier-free Guidance for Zero-shot Text-to-speech","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Economic and Technological Innovation","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Limiting; Fidelity; Speech synthesis; Similarity (geometry); Adaptability; Image (mathematics)","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":[0.0002650183,0.0001433034,0.0002840867,0.000402597,0.0001563684,0.0000338764,0.0005621374,0.0001889337,0.000079183],"category_scores_gemma":[0.0002817929,0.0001873033,0.0001071485,0.001101424,0.00007261799,0.0001953432,0.0001603885,0.0001484349,0.0002915366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002871568,"about_ca_system_score_gemma":0.00002677828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006031876,"about_ca_topic_score_gemma":0.000045606,"domain_scores_codex":[0.9987532,0.00000702997,0.0003095737,0.0006372712,0.000007161355,0.0002857932],"domain_scores_gemma":[0.9990947,0.00008846076,0.000176738,0.0005022281,0.00008672371,0.00005118489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000463886,0.00005037431,0.01995638,0.00001399072,0.0000480341,0.000002497468,0.00001300471,0.0006046426,0.0000573053,0.9681385,0.0103973,0.0006715368],"study_design_scores_gemma":[0.0009172419,0.0001006321,0.01398303,0.00001762247,0.00000906128,3.901446e-7,0.0000517476,0.01165611,0.0007609872,0.9226126,0.04962521,0.000265361],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4540082,0.00009607548,0.4150352,0.001087021,0.0003006211,0.0004738022,0.0001144073,0.00016693,0.1287178],"genre_scores_gemma":[0.981091,0.00002309836,0.001502953,0.0007208125,0.00002633385,0.000006925308,0.000008285295,0.00001129762,0.01660926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5270829,"threshold_uncertainty_score":0.7638007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1150904945180027,"score_gpt":0.1966342250537717,"score_spread":0.081543730535769,"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."}}