{"id":"W2029459011","doi":"10.1155/2008/258184","title":"On the Use of Complementary Spectral Features for Speaker Recognition","year":2007,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Additive white Gaussian noise; Mel-frequency cepstrum; Speech recognition; Computer science; Cepstrum; Vocal tract; Pattern recognition (psychology); Crest factor; Linear prediction; Speaker recognition; Noise (video); White noise; Artificial intelligence; Mathematics; 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":[0.001073251,0.0001481555,0.0001760615,0.0002534483,0.0002389239,0.000205515,0.0003762771,0.00003394684,0.00009415034],"category_scores_gemma":[0.0002069213,0.00009919491,0.0001016676,0.0003352751,0.00006331354,0.001122054,0.00002306694,0.0003526636,0.000006939243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007349873,"about_ca_system_score_gemma":0.00004039838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001084205,"about_ca_topic_score_gemma":0.00001716367,"domain_scores_codex":[0.998508,0.0001010375,0.0004539017,0.0002161094,0.0004158573,0.0003050489],"domain_scores_gemma":[0.9978492,0.001454388,0.0003577638,0.0001122885,0.0001551976,0.00007111346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002840396,0.0001376841,0.00014419,0.00002107324,0.000008094084,0.0000376427,0.0002077823,0.0002375847,0.0008652513,0.002013342,0.0004760672,0.9955673],"study_design_scores_gemma":[0.006302948,0.004047405,0.02029216,0.005796858,0.00007462863,0.001588546,0.002100648,0.03116967,0.3938814,0.4639643,0.0689115,0.001870022],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09635004,0.0007473969,0.8962305,0.002577377,0.0004803039,0.0004078286,0.0000138799,0.00004753047,0.00314512],"genre_scores_gemma":[0.8338726,0.0001268048,0.1619614,0.003669031,0.0002955669,0.000006399962,0.000003632844,0.00001785705,0.00004667444],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9936972,"threshold_uncertainty_score":0.4045051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08896500203753117,"score_gpt":0.3259021926772365,"score_spread":0.2369371906397054,"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."}}