{"id":"W2054060258","doi":"10.1109/icassp.2014.6853889","title":"JFA-based front ends for speaker recognition","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"National Institute of Standards and Technology; Johns Hopkins University","keywords":"NIST; Computer science; Speaker recognition; Normalization (sociology); Speech recognition; Adaptation (eye); Diagonal; Feature extraction; Artificial intelligence; Pattern recognition (psychology); Mathematics","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":[0.002387595,0.001693813,0.001018299,0.001482201,0.001151881,0.00203277,0.001939295,0.002006775,0.01569336],"category_scores_gemma":[0.006291893,0.0008038327,0.001995046,0.0009958679,0.0006854662,0.002081051,0.001762834,0.003043889,0.02176596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000902346,"about_ca_system_score_gemma":0.001161874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005602665,"about_ca_topic_score_gemma":0.007493586,"domain_scores_codex":[0.9984117,0.0003164103,0.0001058109,0.0003933095,0.000596237,0.0001765303],"domain_scores_gemma":[0.9973243,0.0009572472,0.00009494831,0.0005485932,0.0009770399,0.00009778551],"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":[0.0006085512,0.0001835554,0.0008276051,0.0001846344,0.0002076611,0.0001480756,0.0002142418,0.0425776,0.070562,0.01739812,0.01300119,0.8540868],"study_design_scores_gemma":[0.00002739557,0.0001248309,0.001083635,0.00004605755,0.00004833239,0.0002769387,0.00004657048,0.9126462,0.04750033,0.02121679,0.01689073,0.00009208862],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001727018,0.0001386676,0.991654,0.0000532805,0.0001006027,0.00003802309,0.0001764732,0.00510842,0.001003426],"genre_scores_gemma":[0.0905002,0.0002350593,0.8966304,0.0003221772,0.0002178208,0.0003303516,0.001730727,0.001005382,0.009027832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01569336,"threshold_uncertainty_score":0.05249953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03535858043039168,"score_gpt":0.2393011804715223,"score_spread":0.2039426000411306,"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."}}