{"id":"W2400893182","doi":"10.1109/icassp.2016.7472725","title":"Feature mapping, score-, and feature-level fusion for improved normal and whispered speech speaker verification","year":2016,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Speech recognition; Computer science; Mel-frequency cepstrum; Word error rate; Feature (linguistics); Fusion; Vocal tract; Speaker verification; Sensor fusion; Complementarity (molecular biology); Feature extraction; Speaker recognition; Test data; Pattern recognition (psychology); Artificial intelligence","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":[0.0002307081,0.0001527585,0.0001507089,0.0001048563,0.0001442017,0.000170707,0.0002114736,0.0001333876,0.00005406088],"category_scores_gemma":[0.00009819229,0.00009699458,0.00004435414,0.0001316743,0.00004989402,0.0004776126,0.0001100157,0.00006005396,0.00002002084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002333775,"about_ca_system_score_gemma":0.00002730072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001009287,"about_ca_topic_score_gemma":0.00004674756,"domain_scores_codex":[0.9990537,0.00002653907,0.0001131343,0.0004536813,0.0001204604,0.0002325133],"domain_scores_gemma":[0.9992579,0.0001114745,0.0000704154,0.0003080975,0.0001280874,0.000124041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002746949,0.00002170803,0.0006800889,0.00001589999,0.00001221762,0.00000116678,0.00009684451,4.540907e-9,0.1205383,0.002314591,0.01208429,0.8642074],"study_design_scores_gemma":[0.00673531,0.0004621445,0.2927845,0.0003060066,0.00005452033,0.0004841002,0.0002310529,0.02265645,0.2864829,0.006000502,0.382192,0.001610516],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1215861,0.0001817323,0.837086,0.03507055,0.0004646125,0.0008488583,0.00005364404,0.0002642815,0.004444252],"genre_scores_gemma":[0.1669401,0.0003140774,0.8007458,0.00162425,0.0001992038,0.0000568691,0.00001547383,0.00002611538,0.03007801],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8625969,"threshold_uncertainty_score":0.3955324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03598910046254787,"score_gpt":0.2347791838794743,"score_spread":0.1987900834169264,"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."}}