{"id":"W4392411857","doi":"10.1109/ijcb57857.2023.10449225","title":"Benchmark Dataset Dynamics, Bias and Privacy Challenges in Voice Biometrics Research","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Biometrics; Computer science; Benchmark (surveying); Information privacy; Dynamics (music); Internet privacy; Data science; Speech recognition; Data mining; Artificial intelligence; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05816102,0.0007265889,0.0007735931,0.003475799,0.001763274,0.005562511,0.00296914,0.001636032,0.001456625],"category_scores_gemma":[0.1612499,0.0002596876,0.0008620946,0.005280019,0.002258823,0.005221325,0.004619754,0.0020641,0.001173054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002308969,"about_ca_system_score_gemma":0.002256785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004168556,"about_ca_topic_score_gemma":0.00504753,"domain_scores_codex":[0.9240955,0.03717363,0.007698782,0.007434952,0.02218373,0.001413362],"domain_scores_gemma":[0.866926,0.05541614,0.009968814,0.03680768,0.02882061,0.002060802],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001919184,0.0007125842,0.2998866,0.002670951,0.001170331,0.0004856997,0.005835425,0.01450558,0.01662151,0.04027724,0.1196115,0.4963033],"study_design_scores_gemma":[0.0003510047,0.001475207,0.3359375,0.002752277,0.00059894,0.003710834,0.009472013,0.05695041,0.04184385,0.07111587,0.4752358,0.0005562454],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.77049,0.02732937,0.09501436,0.02479985,0.002896715,0.001418547,0.04438667,0.004839557,0.02882496],"genre_scores_gemma":[0.8202466,0.003116291,0.08349178,0.003750925,0.0007415551,0.001546215,0.08228271,0.001193384,0.003630467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.941839,"threshold_uncertainty_score":0.3075886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4262250165150658,"score_gpt":0.4011914368871123,"score_spread":0.02503357962795355,"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."}}