{"id":"W4312904577","doi":"10.1007/978-3-031-20980-2_29","title":"An Analytic Study on Clustering-Based Pseudo-labels for Self-supervised Deep Speaker Verification","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Overfitting; Computer science; Cluster analysis; Discriminative model; Artificial intelligence; Embedding; Pattern recognition (psychology); Set (abstract data type); Speaker recognition; Scheme (mathematics); Speech recognition; Machine learning; Artificial neural network; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001418697,0.0005611362,0.0005607706,0.001178565,0.0005218229,0.0006894679,0.003353863,0.0001898588,0.0001563824],"category_scores_gemma":[0.00009378439,0.0005455418,0.0001871036,0.0007647499,0.0001622486,0.0005553966,0.0003856573,0.0005324956,0.00004304622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005210024,"about_ca_system_score_gemma":0.0004347683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001543083,"about_ca_topic_score_gemma":0.0001681972,"domain_scores_codex":[0.9953915,0.0001271363,0.0005892832,0.002063605,0.001238333,0.0005900946],"domain_scores_gemma":[0.9963977,0.0007475256,0.0002906496,0.002068458,0.0002759853,0.0002196559],"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":[0.00005633134,0.0008600366,0.0001633399,0.00005622844,0.00004921011,0.0000749119,0.001971857,0.06861929,0.0001912017,0.001948782,0.00001415756,0.9259946],"study_design_scores_gemma":[0.0007754933,0.001347855,0.0003764443,0.00006191876,0.00003040761,0.00001530733,0.000002111831,0.9901259,0.0004400324,0.005493708,0.0006674683,0.0006633308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0011226,0.00002303892,0.9942148,0.0004951489,0.001245502,0.001528152,0.0000137327,0.0003570139,0.000999967],"genre_scores_gemma":[0.3807407,0.000006111602,0.6155217,0.003104438,0.0002819099,0.0001668214,0.00002870187,0.00007213679,0.00007741858],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9253313,"threshold_uncertainty_score":0.9996996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03380490464928443,"score_gpt":0.2764592676533605,"score_spread":0.2426543630040761,"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."}}