{"id":"W4401110548","doi":"10.1109/cai59869.2024.00186","title":"On the influence of metric learning loss functions for robust self-supervised speaker verification to label noise","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","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; Government of Canada","keywords":"Computer science; Metric (unit); Speech recognition; Noise (video); Speaker verification; Speaker recognition; Artificial intelligence; Robustness (evolution); Pattern recognition (psychology); Engineering","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":[0.01369942,0.001937463,0.001071471,0.0008253236,0.0007460276,0.001385359,0.001615856,0.001652433,0.0009584182],"category_scores_gemma":[0.03449799,0.0003625482,0.0006278289,0.0005440657,0.001945206,0.002488097,0.001877301,0.002316606,0.0004877128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001058354,"about_ca_system_score_gemma":0.001193601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003001125,"about_ca_topic_score_gemma":0.00278898,"domain_scores_codex":[0.9942807,0.00338259,0.0002428307,0.0008450304,0.001025887,0.0002229421],"domain_scores_gemma":[0.9826061,0.01245307,0.0008385846,0.001787875,0.001996333,0.0003180845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001020145,0.000430377,0.004459211,0.0002945707,0.0002627515,0.0001556811,0.0001899367,0.7580623,0.02542807,0.008185147,0.002824239,0.1986876],"study_design_scores_gemma":[0.0000199969,0.000309563,0.001103952,0.00003637394,0.00002416185,0.0000925504,0.00003437043,0.9833309,0.01292781,0.001589425,0.0005070072,0.00002401235],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1935834,0.001937283,0.7978109,0.0007901686,0.0001417947,0.0002042259,0.0001353046,0.001524718,0.003872226],"genre_scores_gemma":[0.8041386,0.0007126844,0.1913584,0.0004460577,0.00009408022,0.0002002867,0.0005014763,0.0004107878,0.002137681],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01369942,"threshold_uncertainty_score":0.07245034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03583955789924512,"score_gpt":0.2552282605859905,"score_spread":0.2193887026867454,"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."}}