{"id":"W4401110697","doi":"10.1109/cai59869.2024.00077","title":"Contrastive Information Maximization Clustering for Self-Supervised Speaker Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Algorithms and Applications","field":"Engineering","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; Cluster analysis; Speaker recognition; Artificial intelligence; Speech recognition; Pattern recognition (psychology); Natural language processing","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":[0.001923419,0.001014662,0.0006861832,0.0007245474,0.0005380625,0.0006151549,0.001457765,0.001063968,0.001657744],"category_scores_gemma":[0.003909249,0.0005246829,0.0007638592,0.0005518656,0.001050056,0.001054196,0.001405445,0.001687135,0.001081352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008687385,"about_ca_system_score_gemma":0.0009793306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00179553,"about_ca_topic_score_gemma":0.002819777,"domain_scores_codex":[0.9991179,0.0003510687,0.00003495506,0.0002167768,0.0002231983,0.00005614504],"domain_scores_gemma":[0.998791,0.000561044,0.0001410023,0.0002049912,0.0002544624,0.00004751802],"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":[0.0002794622,0.0001290362,0.001096576,0.000180465,0.000149035,0.00007039129,0.0002905914,0.6434838,0.03551892,0.02548777,0.003632621,0.2896814],"study_design_scores_gemma":[0.00000416378,0.00002507575,0.0001393474,0.00000489234,0.000004147508,0.0000170982,0.000007694939,0.9895669,0.005838708,0.003788491,0.000594742,0.000008681225],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005653617,0.00008776846,0.993153,0.00005670737,0.0000111301,0.00002762403,0.00002302417,0.0004925306,0.0004946772],"genre_scores_gemma":[0.2640687,0.0001552543,0.7318554,0.0001523369,0.00004497453,0.0001971221,0.0003250797,0.0003638977,0.002837202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001923419,"threshold_uncertainty_score":0.01017207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009446590667944392,"score_gpt":0.2144447299827798,"score_spread":0.2049981393148354,"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."}}