{"id":"W2962989420","doi":"10.21437/interspeech.2019-2240","title":"A Deep Neural Network for Short-Segment Speaker Recognition","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speech recognition; Speaker recognition; Artificial neural network; Task (project management); Duration (music); Phone; Time delay neural network; Pattern recognition (psychology); Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004489037,0.0003294307,0.0003993372,0.0001193154,0.00009397855,0.0004186064,0.0008740352,0.00029298,0.0004636516],"category_scores_gemma":[0.00005451715,0.0002993528,0.0003898162,0.0001364107,0.0000205224,0.0001924496,0.0007538701,0.0003044217,0.0005313918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008475504,"about_ca_system_score_gemma":0.00006933713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001699494,"about_ca_topic_score_gemma":0.00005116759,"domain_scores_codex":[0.9977832,0.00009229587,0.0004316268,0.0008926193,0.000322183,0.0004780126],"domain_scores_gemma":[0.9983827,0.0002747679,0.0001349158,0.0008513904,0.0002212492,0.0001349004],"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":[0.00001866207,0.00006995406,0.0001097489,0.00008456527,0.00007651503,0.000006345802,0.00006940921,0.001888608,0.00001361184,0.0006773547,0.01305008,0.9839351],"study_design_scores_gemma":[0.0002922237,0.00008495077,0.0006168083,0.0001157971,0.00005320512,0.00002098456,0.00002263236,0.9641141,0.0008634958,0.02634212,0.006787739,0.0006858897],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001901391,0.0001275444,0.9739017,0.001015997,0.003749929,0.001376943,0.00002139646,0.00039349,0.01751154],"genre_scores_gemma":[0.04697987,0.00009351288,0.9451555,0.00349837,0.001293031,0.0006310759,0.0003130147,0.00005317858,0.001982426],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9832492,"threshold_uncertainty_score":0.9999459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06662587784503783,"score_gpt":0.2763267100300315,"score_spread":0.2097008321849937,"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."}}