{"id":"W2062003163","doi":"10.1007/s12559-012-9197-5","title":"Low-variance Multitaper Mel-frequency Cepstral Coefficient Features for Speech and Speaker Recognition Systems","year":2012,"lang":"en","type":"article","venue":"Cognitive Computation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec; Computer Research Institute of Montréal; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Multitaper; Speech recognition; Window function; Computer science; Cepstrum; Mel-frequency cepstrum; Hamming code; NIST; Estimator; Pattern recognition (psychology); Spectral density; Artificial intelligence; Algorithm; Feature extraction; Mathematics; Statistics; 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":[0.00051957,0.0002424597,0.0002478288,0.0001867861,0.0002462242,0.0002959386,0.0001285417,0.0001272361,0.00002164868],"category_scores_gemma":[0.0004081466,0.0002374556,0.00008800173,0.0002907851,0.00008254016,0.000903769,0.00006132163,0.0001319892,0.0001485223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000667248,"about_ca_system_score_gemma":0.00004222004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001783308,"about_ca_topic_score_gemma":0.000004590345,"domain_scores_codex":[0.9982728,0.0001768635,0.0003284556,0.0004741611,0.0002955783,0.0004521646],"domain_scores_gemma":[0.9981167,0.0007250977,0.0001870776,0.00008961782,0.0006815705,0.0001999726],"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":[0.00004491,0.0003320681,0.0005555531,0.0001390239,0.00006592645,0.000008889569,0.00092372,0.00001640094,0.00152933,0.001443898,0.0007650798,0.9941752],"study_design_scores_gemma":[0.01251061,0.001265917,0.2258038,0.002757084,0.0005613586,0.001489899,0.005716867,0.6294314,0.101446,0.0130278,0.001578158,0.004411141],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09975318,0.0005393796,0.8949568,0.0001509452,0.001247657,0.0009801936,0.00008329059,0.0001920238,0.002096483],"genre_scores_gemma":[0.9407571,0.000028062,0.05810339,0.000357578,0.0003332798,0.0001388908,0.0001504706,0.00002224333,0.000108983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.989764,"threshold_uncertainty_score":0.9683157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03785654066309455,"score_gpt":0.2835100555252821,"score_spread":0.2456535148621875,"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."}}