{"id":"W3006824058","doi":"10.1109/asru46091.2019.9003792","title":"Development of Voice Spoofing Detection Systems for 2019 Edition of Automatic Speaker Verification and Countermeasures Challenge","year":2019,"lang":"en","type":"article","venue":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Spoofing attack; Computer science; Convolutional neural network; Speaker verification; Speech recognition; Mel-frequency cepstrum; Speaker recognition; Artificial intelligence; Frame (networking); Bottleneck; Pattern recognition (psychology); Classifier (UML); Replay attack; Biometrics; Feature extraction; Artificial neural network; Authentication (law); Computer security","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001249771,0.0002770513,0.0005142058,0.0004790059,0.0001944244,0.000176033,0.0002042321,0.0002164382,0.00004666676],"category_scores_gemma":[0.0001352231,0.0002747724,0.00009279136,0.0003386596,0.0000869167,0.000723689,0.00004060131,0.0001294964,0.0000542686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002234896,"about_ca_system_score_gemma":0.000091768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001754011,"about_ca_topic_score_gemma":0.00002805008,"domain_scores_codex":[0.9976944,0.0001236094,0.0008686074,0.0005012067,0.000505587,0.000306547],"domain_scores_gemma":[0.9979218,0.0006826791,0.0006984642,0.0003343899,0.0002535103,0.0001091965],"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":[0.00008173421,0.0003088023,0.0001317177,0.002970911,0.0002991848,0.000002270813,0.004182758,0.00001474498,0.0248223,0.001101536,0.0009324028,0.9651516],"study_design_scores_gemma":[0.005472602,0.0005617881,0.003987222,0.007819583,0.0003335565,0.0002535614,0.01345995,0.8598724,0.09468728,0.01091957,0.000967224,0.001665284],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4879157,0.0003239747,0.5082202,0.0001296633,0.001285614,0.00125074,0.00003516366,0.0002106946,0.0006282572],"genre_scores_gemma":[0.9414563,0.0003144451,0.05783852,0.00003562443,0.00006930471,0.00006804353,0.00004879171,0.00003259495,0.0001363576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9634864,"threshold_uncertainty_score":0.9999704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08200242944652283,"score_gpt":0.2663433709157091,"score_spread":0.1843409414691863,"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."}}