{"id":"W4408353205","doi":"10.1109/icassp49660.2025.10888609","title":"AdaptiveDrop: A Simple Adaptive Label Noise Filtering Scheme for Enhanced Self-supervised Speaker Verification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Scheme (mathematics); Speaker verification; Speech recognition; Simple (philosophy); Noise (video); Noise measurement; Adaptive filter; Speaker recognition; Artificial intelligence; Pattern recognition (psychology); Algorithm; Noise reduction; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00208812,0.00103983,0.001101667,0.0008405981,0.0006913478,0.0007173948,0.002803473,0.001815382,0.002488386],"category_scores_gemma":[0.003473801,0.0005064327,0.0006723797,0.0005240543,0.0009398709,0.0020066,0.002361263,0.002011318,0.00189693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000568113,"about_ca_system_score_gemma":0.001098267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002356004,"about_ca_topic_score_gemma":0.00623863,"domain_scores_codex":[0.9987531,0.0002908384,0.00004534963,0.0003750644,0.0004265092,0.0001091275],"domain_scores_gemma":[0.998332,0.0003911375,0.0001244237,0.0005608608,0.000506914,0.00008483502],"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":[0.0005628451,0.0002550654,0.001584381,0.0001534543,0.0001201111,0.0001441518,0.0002863274,0.05423372,0.1168511,0.005516312,0.007499169,0.8127934],"study_design_scores_gemma":[0.00004202819,0.0001488129,0.0006494996,0.00001347852,0.00002596572,0.0001738706,0.00003921989,0.9126173,0.07805196,0.003612113,0.004585884,0.00003992659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01159958,0.0001229918,0.9840974,0.00008226197,0.00005322951,0.00005647585,0.00006347141,0.003312675,0.0006118095],"genre_scores_gemma":[0.202149,0.0001112639,0.790595,0.0002997129,0.00007239107,0.0001685121,0.0004694893,0.0005552017,0.00557935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002803473,"threshold_uncertainty_score":0.01104313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02397464787069947,"score_gpt":0.275319425567589,"score_spread":0.2513447776968895,"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."}}