{"id":"W4400926002","doi":"10.1007/s11042-024-19892-4","title":"Deep normalization for light SpineNet speaker anti-spoofing systems","year":2024,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Normalization (sociology); Speaker verification; Speech recognition; Artificial intelligence; Spoofing attack; Computer security; Speaker recognition","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001421278,0.00009788801,0.0001108386,0.00008994614,0.0001369809,0.000585349,0.0001808433,0.00005443891,0.00001664747],"category_scores_gemma":[0.00002660265,0.00008627872,0.0000447323,0.0002701408,0.00001814095,0.0003514668,0.00003976829,0.00004453607,0.0001299845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001521869,"about_ca_system_score_gemma":0.00002224717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006998429,"about_ca_topic_score_gemma":0.000003656804,"domain_scores_codex":[0.9992276,0.00001333607,0.0001910462,0.0003118395,0.0001019365,0.0001541787],"domain_scores_gemma":[0.9994186,0.0001843012,0.00003412482,0.0002144057,0.00006906737,0.0000794955],"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":[9.725971e-7,0.00004073298,0.0001065606,0.0001432563,0.0000261246,0.000002048811,0.000264278,0.00009258121,0.003228301,0.06790789,0.001735413,0.9264519],"study_design_scores_gemma":[0.0001028459,0.000008182443,0.000676278,0.00003332896,0.00001332426,0.000012414,0.00002772325,0.7065613,0.001730147,0.000433844,0.2902758,0.0001248107],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000399757,0.001080854,0.9944524,0.0009587589,0.0002464449,0.0007231725,0.00003349522,0.0002526458,0.001852508],"genre_scores_gemma":[0.5133971,0.0009289903,0.4764263,0.0006365326,0.00198399,0.00426615,0.0003941557,0.00007508882,0.001891679],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.926327,"threshold_uncertainty_score":0.5644534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02683028761416486,"score_gpt":0.2627760932517972,"score_spread":0.2359458056376324,"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."}}