{"id":"W2900688537","doi":"10.1109/taslp.2018.2882731","title":"Privacy-Preserving iVector-Based Speaker Verification","year":2018,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Password; Alphanumeric; Speaker recognition; Biometrics; Domain (mathematical analysis); Authentication (law); Speech recognition; Voice over IP; Computer security; World Wide Web; The Internet","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":[0.0002599121,0.000212748,0.0001829384,0.0002674848,0.0005052816,0.0003793866,0.0006833546,0.0001048285,0.0004013951],"category_scores_gemma":[0.00009928511,0.0001994563,0.00007545898,0.0005587935,0.0001099769,0.0005764852,0.00001434062,0.0002107812,0.0001528998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005500197,"about_ca_system_score_gemma":0.0001050686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005107652,"about_ca_topic_score_gemma":0.00006652746,"domain_scores_codex":[0.9984887,0.00007572288,0.0002439967,0.0005416152,0.0003202308,0.0003297702],"domain_scores_gemma":[0.998718,0.0001080267,0.000108658,0.000746794,0.0001606117,0.0001579333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000276618,0.0001086312,0.00004404952,0.00005072417,0.00001487953,0.00001837121,0.001499225,0.000008329409,0.02138824,0.00001081821,0.0001069505,0.9767221],"study_design_scores_gemma":[0.001109115,0.0002464789,0.001729199,0.0003630527,0.00005496401,0.0001243336,0.0006510566,0.07049116,0.9198617,0.0006927885,0.003959957,0.0007162535],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09756935,0.0002203981,0.8975723,0.001557314,0.0002864438,0.0001835492,0.000007390688,0.0004271271,0.002176136],"genre_scores_gemma":[0.7925228,0.00001546444,0.206021,0.0008673102,0.0001248758,0.0000217034,0.000002684973,0.00002052954,0.0004036076],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9760059,"threshold_uncertainty_score":0.8133593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02376216840936063,"score_gpt":0.2747718836450715,"score_spread":0.2510097152357109,"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."}}