{"id":"W2919923656","doi":"10.1007/s42452-019-0305-y","title":"Multitaper MFCC and normalized multitaper phase-based features for speaker verification","year":2019,"lang":"en","type":"article","venue":"SN Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Multitaper; Computer science; Mel-frequency cepstrum; Speech recognition; Mixture model; Cepstrum; Artificial intelligence; Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005867186,0.0001425144,0.0001706468,0.0001483566,0.0002703177,0.0003129937,0.0005307785,0.00006536152,0.0001361077],"category_scores_gemma":[0.00005112776,0.0001120648,0.00005849275,0.000353298,0.0001834213,0.0003436605,0.00004875591,0.00006104652,0.0001665559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001676965,"about_ca_system_score_gemma":0.00007169788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000113733,"about_ca_topic_score_gemma":0.00001329813,"domain_scores_codex":[0.9986295,0.00002692502,0.0001734606,0.0005646143,0.0003207075,0.0002848],"domain_scores_gemma":[0.999193,0.0002896299,0.00007935551,0.0002858434,0.0000635061,0.00008868764],"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":[0.0001597844,0.0004298476,0.001253722,0.00008044935,0.00003172622,0.000001458666,0.001216513,0.0001302317,0.3294832,0.1079635,0.002770056,0.5564796],"study_design_scores_gemma":[0.0116918,0.0006084919,0.01024741,0.00007022399,0.00004376533,0.00002129217,0.0010957,0.4361765,0.4041247,0.005440219,0.1289578,0.001522138],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5281349,0.0002898934,0.3883621,0.003555501,0.001322997,0.003001843,0.00004780319,0.000588043,0.07469685],"genre_scores_gemma":[0.7977309,0.000005656128,0.2008016,0.0009963855,0.0000309368,0.00009288131,0.000006242997,0.000006470368,0.0003289548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5549574,"threshold_uncertainty_score":0.4569871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02431220456103804,"score_gpt":0.2856369015459819,"score_spread":0.2613246969849438,"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."}}