{"id":"W4404238744","doi":"10.1109/ijcb62174.2024.10744521","title":"On the influence of regularization techniques on label noise robustness: Self-supervised speaker verification as a use case","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Robustness (evolution); Speaker verification; Computer science; Speech recognition; Regularization (linguistics); Speaker recognition; Artificial intelligence; Pattern recognition (psychology); Noise measurement; Noise reduction","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003233375,0.0001170676,0.00009324399,0.0001649745,0.00008630255,0.0002719247,0.0002994767,0.00007034691,0.00008919618],"category_scores_gemma":[0.0002348744,0.00007700506,0.00004554523,0.0006035271,0.00003317738,0.0005422544,0.00004413279,0.0001003801,0.0001244187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004092557,"about_ca_system_score_gemma":0.00005642706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000729228,"about_ca_topic_score_gemma":0.000007981025,"domain_scores_codex":[0.9989811,0.0001156684,0.0002080147,0.0003142401,0.0002691309,0.0001118492],"domain_scores_gemma":[0.9987346,0.0004429741,0.00004655461,0.0005811882,0.0001540247,0.00004064862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003667453,0.00051112,0.00005116853,0.00009270987,0.00006749747,0.0003957728,0.001295201,0.0005658874,0.02474026,0.7215092,0.00235247,0.248382],"study_design_scores_gemma":[0.0001994994,0.0002886983,0.0006056028,0.000403464,0.0000345107,0.0004669905,0.00009793868,0.6650997,0.3237585,0.006734926,0.001945817,0.0003642713],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8736559,0.00000885158,0.1182651,0.002272936,0.00008188109,0.0004238221,0.000004732472,0.0007987177,0.004488041],"genre_scores_gemma":[0.9298693,0.00002812288,0.06830958,0.001038376,0.0000164773,0.00005524846,0.000003014895,0.00001255392,0.0006673297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7147743,"threshold_uncertainty_score":0.3140175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02842436391590777,"score_gpt":0.2556727641753869,"score_spread":0.2272484002594791,"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."}}