{"id":"W2028124797","doi":"10.1016/j.specom.2012.08.007","title":"Multitaper MFCC and PLP features for speaker verification using i-vectors","year":2012,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":false,"ca_institutions":"Computer Research Institute of Montréal; Institut National de la Recherche Scientifique","funders":"National Institute of Standards and Technology","keywords":"Multitaper; Mel-frequency cepstrum; Computer science; NIST; Speech recognition; Pattern recognition (psychology); Cepstrum; Speaker recognition; Artificial intelligence; Feature extraction","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":[0.0006205595,0.0008454508,0.000673186,0.0009052348,0.0004476138,0.0006890895,0.0006981821,0.0009408582,0.008409541],"category_scores_gemma":[0.001920444,0.0002970834,0.000549058,0.0007724473,0.0001981853,0.001206433,0.0007493768,0.0007075911,0.006367714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001609732,"about_ca_system_score_gemma":0.000481638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001633215,"about_ca_topic_score_gemma":0.002725732,"domain_scores_codex":[0.9993823,0.0001371816,0.00005699903,0.0001172361,0.0002271194,0.00007923795],"domain_scores_gemma":[0.9991406,0.0002609389,0.00006564814,0.0001652935,0.000326277,0.00004124333],"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":[0.0008391078,0.0001218214,0.0006279353,0.0001657283,0.00004409647,0.00008726698,0.00004650228,0.00316787,0.2133023,0.0009559232,0.003361669,0.7772799],"study_design_scores_gemma":[0.0001427442,0.000774202,0.01357831,0.0001034659,0.0002794371,0.0008954371,0.0001768461,0.3657354,0.5995418,0.001725338,0.0169152,0.0001317978],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0710517,0.001897294,0.9137853,0.0002267672,0.0002148627,0.0001599411,0.001314508,0.00588133,0.005468351],"genre_scores_gemma":[0.4398955,0.001366983,0.5414621,0.0001367663,0.0001710847,0.0002752524,0.004607956,0.0005263121,0.01155788],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008409541,"threshold_uncertainty_score":0.02813268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03390941946555964,"score_gpt":0.2998207171212208,"score_spread":0.2659112976556612,"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."}}