{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002683276,0.00007757419,0.0001124276,0.001999792,0.00008352401,0.000170128,0.0006761656,0.000061799,0.00004969475],"category_scores_gemma":[0.001196057,0.0000684645,0.00001490982,0.004212445,0.00005825453,0.0003245929,0.0007785571,0.0001531112,0.0005919468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004549381,"about_ca_system_score_gemma":0.00003358183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001182192,"about_ca_topic_score_gemma":0.0004363035,"domain_scores_codex":[0.9984666,0.0002005298,0.0001641044,0.000419736,0.0004120725,0.000336951],"domain_scores_gemma":[0.9978998,0.001402984,0.00002142816,0.0005036847,0.00006972911,0.0001024263],"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":[0.00000217413,0.00006444926,0.001428093,0.00003121476,0.000006003571,0.00007135445,0.0002821776,3.253456e-7,0.00003254599,0.0236265,0.02546168,0.9489935],"study_design_scores_gemma":[0.001066415,0.0002546812,0.1561844,0.000112,0.000004766514,0.0000601599,0.002759377,0.4459919,0.001773147,0.03996762,0.3510166,0.000808975],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5439138,0.007728118,0.03371274,0.2297591,0.002247215,0.002654965,0.00233576,0.002788866,0.1748594],"genre_scores_gemma":[0.8310353,0.04199938,0.1209919,0.0009467737,0.0001957893,0.0001327301,0.001534797,0.00005740253,0.003105966],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9481845,"threshold_uncertainty_score":0.7608476,"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."}}