{"id":"W4313042211","doi":"10.1109/ijcnn55064.2022.9892054","title":"Fine-grained Early Frequency Attention for Deep Speaker Recognition","year":2022,"lang":"en","type":"article","venue":"2022 International Joint Conference on Neural Networks (IJCNN)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Focus (optics); Deep neural networks; Deep learning; Artificial intelligence; Key (lock); Artificial neural network; Speech recognition; Pattern recognition (psychology)","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004521145,0.0002742956,0.0002449346,0.0003175073,0.0004080842,0.0003628245,0.0009809788,0.00007408558,0.003849839],"category_scores_gemma":[0.0001304409,0.0002838207,0.0002974342,0.0003555859,0.00004465758,0.0005444111,0.0003147114,0.0004492055,0.00009361592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001895001,"about_ca_system_score_gemma":0.00005193719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003141338,"about_ca_topic_score_gemma":0.00004871562,"domain_scores_codex":[0.9973899,0.000177689,0.0005341503,0.0007227422,0.0007689426,0.0004066288],"domain_scores_gemma":[0.9985626,0.0002192947,0.0003195655,0.0003628469,0.0004034755,0.0001322007],"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":[0.0004603709,0.001052307,0.0007708141,0.00002329329,0.0002697663,0.0001518285,0.0003470566,0.004843795,0.005578844,0.156735,0.01501979,0.8147471],"study_design_scores_gemma":[0.001442133,0.0004771664,0.003569694,0.00005034882,0.00001504435,0.0001054533,0.0000605988,0.9679855,0.00020754,0.02325362,0.002367271,0.0004656721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04104658,0.0000266698,0.9125664,0.01770301,0.006854868,0.004103331,0.0002270885,0.0006249438,0.01684705],"genre_scores_gemma":[0.9742796,0.00001240343,0.01497864,0.002474787,0.0007043949,0.0053546,0.0005132386,0.00004301398,0.001639256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9631417,"threshold_uncertainty_score":0.9999614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05429654350573929,"score_gpt":0.2565625299664059,"score_spread":0.2022659864606666,"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."}}