{"id":"W2169890399","doi":"10.1007/978-3-642-25020-0_32","title":"Comparative Evaluation of Feature Normalization Techniques for Speaker Verification","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"Computer Research Institute of Montréal; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Normalization (sociology); NIST; Computer science; Speaker verification; Linear discriminant analysis; Speech recognition; Pattern recognition (psychology); Artificial intelligence; Probabilistic logic; Feature vector; Feature (linguistics); Speaker recognition","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":[0.001747462,0.0003029525,0.0004257951,0.0007025516,0.0001269254,0.0001320504,0.00124641,0.0002912673,0.00004631543],"category_scores_gemma":[0.0001300295,0.0002801045,0.0001184994,0.0004206004,0.000310906,0.0005607621,0.0001838338,0.0002265926,0.00001197535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002173549,"about_ca_system_score_gemma":0.0004442856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009248796,"about_ca_topic_score_gemma":0.0000465963,"domain_scores_codex":[0.9974706,0.00006528354,0.000414822,0.000831897,0.0009604192,0.0002569631],"domain_scores_gemma":[0.9968997,0.0002534506,0.0004822877,0.0007745919,0.001524765,0.00006521314],"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":[0.00001058455,0.0000348599,0.00001405488,0.00003292108,0.00001296779,6.660458e-7,0.0009676297,0.0004270294,0.0005519665,0.01658692,0.00007310302,0.9812873],"study_design_scores_gemma":[0.0003409491,0.0002275296,0.0003568655,0.0004299714,0.00005605518,0.00002282607,6.111506e-7,0.6143386,0.1437674,0.2372204,0.002645122,0.0005937752],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005347446,0.0001666788,0.9877219,0.0001878352,0.0005457187,0.001082711,0.00001230381,0.000100425,0.01012893],"genre_scores_gemma":[0.1395722,0.00003885166,0.8595831,0.0003025694,0.0001743925,0.00007861241,0.00003802912,0.00002163142,0.0001905145],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9806935,"threshold_uncertainty_score":0.9999651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07976696728653544,"score_gpt":0.3120268597436664,"score_spread":0.232259892457131,"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."}}