{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004421866,0.0007986047,0.0009734551,0.001497887,0.0009170722,0.001969528,0.003167072,0.001611494,0.00450571],"category_scores_gemma":[0.03762906,0.0007334687,0.0008361147,0.001440507,0.002586236,0.005623155,0.002078261,0.002273134,0.0008287071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002275703,"about_ca_system_score_gemma":0.001377266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003639338,"about_ca_topic_score_gemma":0.003835423,"domain_scores_codex":[0.9972263,0.001121426,0.00008376961,0.0005721768,0.0007938885,0.0002023668],"domain_scores_gemma":[0.9704351,0.02315027,0.001165834,0.001862864,0.003062045,0.0003237795],"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":[0.0003736365,0.0001453298,0.002762671,0.0004860674,0.0001075134,0.0002094798,0.0008914091,0.3422729,0.01404904,0.4410318,0.00747931,0.1901909],"study_design_scores_gemma":[0.000003095779,0.00003201917,0.0006200405,0.00003282074,0.0000153046,0.00008414891,0.00005337828,0.953626,0.001510514,0.04307495,0.0009306857,0.00001709838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01796114,0.0008106633,0.9767651,0.0003237433,0.00004646091,0.00005630978,0.00009484281,0.0002097822,0.003731836],"genre_scores_gemma":[0.6586372,0.001426309,0.3236694,0.0003646465,0.0003790665,0.000218908,0.0007141431,0.0005424217,0.01404776],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00450571,"threshold_uncertainty_score":0.02338529,"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."}}