{"id":"W2044054970","doi":"10.1109/asru.2011.6163886","title":"Multi-taper MFCC features for speaker verification using I-vectors","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Computer Research Institute of Montréal","funders":"National Institute of Standards and Technology","keywords":"NIST; Mel-frequency cepstrum; Computer science; Speech recognition; Speaker recognition; Pattern recognition (psychology); Classifier (UML); Speaker verification; Hamming distance; Hamming code; Microphone; Variance (accounting); Artificial intelligence; Feature extraction; Algorithm; Decoding methods; Telecommunications","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":[0.0001168921,0.00007676009,0.00007390636,0.00006640298,0.00008104271,0.00005803488,0.0002558184,0.00004785639,0.0002705008],"category_scores_gemma":[0.00004933788,0.00006240766,0.00006418175,0.0001140471,0.00001703539,0.0002681221,0.00002862381,0.00003244802,0.00008424711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000185081,"about_ca_system_score_gemma":0.00001975319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007963918,"about_ca_topic_score_gemma":0.00002916601,"domain_scores_codex":[0.9994224,0.00002055682,0.0001053818,0.0002239535,0.00008553632,0.0001421467],"domain_scores_gemma":[0.9995425,0.00004016389,0.00003845075,0.0002514244,0.00007526937,0.0000521387],"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":[0.00006168219,0.0007959479,0.005381964,0.00004958647,0.0001301602,0.000009688039,0.005942648,0.000008886801,0.1289164,0.05238489,0.00883203,0.7974861],"study_design_scores_gemma":[0.001236119,0.0001069488,0.1356063,0.0000342117,0.0000414377,0.00006667305,0.000394201,0.2345571,0.6066414,0.002192237,0.01828375,0.0008395592],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02220382,0.00001917517,0.9689353,0.00009376345,0.0003413038,0.0001865727,0.000001704487,0.0001624571,0.008055919],"genre_scores_gemma":[0.2260307,0.000002534463,0.7725333,0.0003393213,0.00002791831,0.00001288607,0.000001299147,0.000006586162,0.001045446],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7966465,"threshold_uncertainty_score":0.2961794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1690514877693239,"score_gpt":0.2935253001225161,"score_spread":0.1244738123531922,"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."}}