{"id":"W2990074387","doi":"10.1109/mlsp.2019.8918703","title":"End-To-End Detection Of Attacks To Automatic Speaker Recognizers With Time-Attentive Light Convolutional Neural Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Convolutional neural network; Benchmark (surveying); Microphone; Word error rate; Speaker recognition; Biometrics; Dimension (graph theory); Set (abstract data type); Spectrogram; Artificial intelligence; Pattern recognition (psychology); 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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002329667,0.0001631866,0.0002389575,0.0002180587,0.00006032103,0.00007639899,0.0003319734,0.00006404149,0.001951529],"category_scores_gemma":[0.00003456235,0.000128882,0.00008182388,0.0006250821,0.00002625234,0.0003141236,0.0001067368,0.0001005136,0.001825779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007945221,"about_ca_system_score_gemma":0.00003687602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003171742,"about_ca_topic_score_gemma":0.00005279619,"domain_scores_codex":[0.9985746,0.00008529782,0.0002672229,0.0004146124,0.0003713637,0.0002868938],"domain_scores_gemma":[0.9990082,0.0001717188,0.0000983437,0.0003341141,0.000208687,0.0001788751],"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":[0.0002376391,0.0003507974,0.005669545,0.00005559813,0.0003720314,0.00002987579,0.001040551,0.003592857,0.03959666,0.001072287,0.006994111,0.9409881],"study_design_scores_gemma":[0.0005807359,0.0005028052,0.01770834,0.00007861065,0.00002612848,0.00006465887,0.0001222515,0.9454791,0.03371109,0.00006114792,0.001276802,0.0003883262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4155889,0.000009304636,0.5663999,0.001566454,0.0005436112,0.0006635477,0.000004895273,0.0002517794,0.01497168],"genre_scores_gemma":[0.9541602,6.522466e-7,0.04187031,0.001063022,0.00005027361,0.00002327711,0.000003364306,0.00001316986,0.002815728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9418862,"threshold_uncertainty_score":0.9989608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009264250930136903,"score_gpt":0.2112065186632133,"score_spread":0.2019422677330764,"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."}}