{"id":"W4393043884","doi":"10.3390/s24061996","title":"Self-Supervised Open-Set Speaker Recognition with Laguerre–Voronoi Descriptors","year":2024,"lang":"en","type":"article","venue":"Sensors","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Speaker recognition; Pattern recognition (psychology); Speech recognition; Artificial intelligence; Open set; Feature extraction; Cluster analysis; Set (abstract data type); Feature (linguistics); Artificial neural network; Biometrics; Speaker diarisation; Voronoi diagram; Neural gas; Time delay neural network; 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":[],"category_scores_codex":[0.0003156351,0.0002103012,0.0001942339,0.0001873131,0.0001286796,0.001005139,0.0006504261,0.00008305131,0.0005117843],"category_scores_gemma":[0.00003263304,0.000167782,0.00007808932,0.000606151,0.00003897289,0.0008145386,0.0001541514,0.0001715736,0.002510019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007397165,"about_ca_system_score_gemma":0.0001006911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007946936,"about_ca_topic_score_gemma":0.00007121162,"domain_scores_codex":[0.9984272,0.0001318911,0.0002176029,0.0005967909,0.0002975882,0.0003289899],"domain_scores_gemma":[0.9991524,0.0001277211,0.00003698224,0.0004309986,0.00009329183,0.0001586069],"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":[0.0000557042,0.0002160198,0.0002283486,0.0001513276,0.0002662037,0.0008175413,0.004401075,0.00000998485,0.0006067372,0.007217213,0.01571286,0.970317],"study_design_scores_gemma":[0.00235223,0.0006827186,0.001766091,0.0009634,0.0002222155,0.001178188,0.002010776,0.5166388,0.05247942,0.007910145,0.4112923,0.002503744],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7809768,0.0003794106,0.03613226,0.004067131,0.002712395,0.001327943,0.00006919979,0.003364704,0.1709702],"genre_scores_gemma":[0.6044796,0.000170235,0.3886591,0.001575634,0.0004028432,0.00009587729,0.00006387517,0.0001016876,0.004451131],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9678133,"threshold_uncertainty_score":0.9982666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04683011915590059,"score_gpt":0.2578130349466004,"score_spread":0.2109829157906998,"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."}}