{"id":"W2128176957","doi":"10.1109/icassp.1982.1171437","title":"A composite scheme for text-independent speaker recognition","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Speech recognition; Speaker recognition; Computer science; Cepstrum; Mel-frequency cepstrum; Inverse filter; Filter (signal processing); Pattern recognition (psychology); Feature (linguistics); Scheme (mathematics); Feature extraction; Linear prediction; Population; Inverse; Artificial intelligence; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002171189,0.000103486,0.0001108755,0.00009677956,0.000095688,0.0001541309,0.0002998971,0.00005502427,0.0006879751],"category_scores_gemma":[0.00003165501,0.00009215456,0.0001003569,0.0001323565,0.00001353726,0.0004481167,0.00005924999,0.00005697863,0.001779351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003946591,"about_ca_system_score_gemma":0.00002158561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005965152,"about_ca_topic_score_gemma":0.00002961289,"domain_scores_codex":[0.9990858,0.00002372848,0.0001885769,0.0002950969,0.0001863069,0.0002205304],"domain_scores_gemma":[0.9994004,0.0001068875,0.0000483015,0.0002341907,0.0001143327,0.00009588362],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009828414,0.0001102958,0.00005353327,0.000005396994,0.0000162592,0.000002021908,0.00006612647,8.253036e-7,0.00481968,0.003630712,0.005734963,0.9855503],"study_design_scores_gemma":[0.002864403,0.0001865007,0.00345511,0.0000691357,0.00002954421,0.000177786,0.0000951473,0.2236086,0.4348532,0.01493143,0.3187127,0.001016454],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02160606,0.00002910682,0.9114367,0.004983898,0.0002008173,0.0003470058,0.000008547077,0.0003784476,0.06100939],"genre_scores_gemma":[0.1125682,0.000008910684,0.8814057,0.002957422,0.0002031527,0.00005924773,0.00001183685,0.00001019514,0.002775422],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9845339,"threshold_uncertainty_score":0.9989979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03756760927467152,"score_gpt":0.2611128798612824,"score_spread":0.2235452705866109,"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."}}