{"id":"W2900022717","doi":"10.1109/icassp.2019.8682064","title":"Generative Adversarial Speaker Embedding Networks for Domain Robust End-to-end Speaker Verification","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal; McGill University","funders":"","keywords":"Discriminator; Speaker verification; Computer science; NIST; Classifier (UML); Speech recognition; End-to-end principle; Adversarial system; Baseline (sea); Artificial intelligence; Generative grammar; Trigonometric functions; Embedding; Dimensionality reduction; Pattern recognition (psychology); Speaker recognition; Mathematics; Detector","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008709362,0.0004640962,0.0005389436,0.0002767186,0.0001866714,0.0006805588,0.001215466,0.0004620232,0.001011196],"category_scores_gemma":[0.0001255169,0.0004379203,0.0003594575,0.0002616353,0.00004193636,0.0003203978,0.0008584883,0.0004263934,0.0004504934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002446494,"about_ca_system_score_gemma":0.0002316272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006224465,"about_ca_topic_score_gemma":0.00007092875,"domain_scores_codex":[0.9968443,0.0001937864,0.000571704,0.001392406,0.0004553055,0.0005425127],"domain_scores_gemma":[0.9975401,0.0003703761,0.0003029319,0.001249306,0.0003133304,0.0002239971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002738603,0.0003447954,0.0001447207,0.0001561136,0.0006812689,0.00002468072,0.003167643,0.4439107,0.001271205,0.07660459,0.08781907,0.3856013],"study_design_scores_gemma":[0.0007229314,0.00006606038,0.0003744838,0.0001076776,0.00004968884,0.00001079604,0.000156721,0.9603734,0.002712568,0.003668663,0.03089766,0.0008593503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001573834,0.00003702145,0.971379,0.001780812,0.00511464,0.001686083,0.00005294183,0.0002686793,0.01810702],"genre_scores_gemma":[0.06972704,0.00003382033,0.9230468,0.001540162,0.001534003,0.0003102401,0.0002271151,0.0000535904,0.003527282],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5164627,"threshold_uncertainty_score":0.999902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04339371839715384,"score_gpt":0.2786855733494646,"score_spread":0.2352918549523108,"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."}}