{"id":"W3195948749","doi":"10.1109/jiot.2021.3097266","title":"Efficient and Privacy-Preserving Speaker Recognition for Cybertwin-Driven 6G","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Euclidean distance; Biometrics; Speaker recognition; Cosine similarity; Random projection; Computation; Computer security; Speech recognition; Data mining; Artificial intelligence; Algorithm; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008689041,0.0006767004,0.000777818,0.0004955336,0.0006330135,0.0007840575,0.0008579723,0.0007542752,0.001406664],"category_scores_gemma":[0.002333508,0.0001873373,0.0004479574,0.0005071114,0.0006690434,0.001656066,0.001705176,0.001120549,0.0008793327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004556257,"about_ca_system_score_gemma":0.0005888792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007485164,"about_ca_topic_score_gemma":0.0008306068,"domain_scores_codex":[0.9982798,0.0003731282,0.0001063882,0.0003012204,0.0007323452,0.0002071061],"domain_scores_gemma":[0.9990722,0.0001956577,0.000108365,0.0003909742,0.0001782651,0.00005442262],"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":[0.001507301,0.0002831636,0.002631177,0.0002511625,0.000174453,0.0008855051,0.0004297038,0.08699644,0.2162379,0.04195876,0.00876937,0.6398751],"study_design_scores_gemma":[0.00006019447,0.0004518061,0.001594523,0.0000276342,0.00006008687,0.001523584,0.0001362135,0.8718428,0.09854973,0.01628824,0.009371542,0.00009363717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07475556,0.000816739,0.9182477,0.0004193666,0.000265537,0.0001359043,0.0002178305,0.001991441,0.003149821],"genre_scores_gemma":[0.8762805,0.0003968574,0.1189801,0.0002963466,0.0001224045,0.00008613647,0.0003988228,0.00004544249,0.003393281],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001406664,"threshold_uncertainty_score":0.004705787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03617530084013353,"score_gpt":0.2618438795747483,"score_spread":0.2256685787346148,"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."}}