{"id":"W4307988784","doi":"10.32920/21428718","title":"On the Use of Complementary Spectral Features for Speaker Recognition","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Additive white Gaussian noise; Mel-frequency cepstrum; Speech recognition; Cepstrum; Crest factor; Vocal tract; Pattern recognition (psychology); Computer science; Speaker recognition; Mathematics; White noise; Artificial intelligence; Bandwidth (computing); Feature extraction; Telecommunications","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":[],"consensus_categories":[],"category_scores_codex":[0.0002257392,0.0001405127,0.0001555209,0.00007495729,0.000148365,0.0002041386,0.0007559146,0.00003991288,0.0006838144],"category_scores_gemma":[0.00005178516,0.00009562697,0.0001390938,0.0000982888,0.00002599958,0.000124294,0.0007748625,0.0003116678,0.000004377961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004623699,"about_ca_system_score_gemma":0.00007280111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008228543,"about_ca_topic_score_gemma":0.00004039381,"domain_scores_codex":[0.9989511,0.00005511845,0.0001950323,0.0003606667,0.0002597404,0.0001782893],"domain_scores_gemma":[0.9988968,0.0003697084,0.0001728571,0.0004770617,0.0000573996,0.00002621451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001864025,0.0004579513,0.0002717143,0.0004216732,0.0003156118,0.00001782549,0.00154387,0.002745489,0.002111405,0.04970714,0.6249307,0.3172902],"study_design_scores_gemma":[0.0009625162,0.0006190424,0.003605265,0.0003630967,0.00007835689,0.00002136984,0.0002843223,0.008766666,0.3398226,0.5935581,0.0509338,0.0009848741],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1477051,0.0002018602,0.8090587,0.02487548,0.002903566,0.002625475,0.0005572886,0.0003722982,0.01170019],"genre_scores_gemma":[0.08996867,0.00003753678,0.8968458,0.01014933,0.0003383603,0.0002247915,0.0004492995,0.0000322497,0.001954031],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5739969,"threshold_uncertainty_score":0.7487289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1379335217981216,"score_gpt":0.3032598930918268,"score_spread":0.1653263712937052,"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."}}