{"id":"W4318148717","doi":"10.1109/tai.2023.3240113","title":"Fine-Grained Early Frequency Attention for Deep Speaker Representation Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Robustness (evolution); Speech recognition; Deep learning; Convolutional neural network; Artificial intelligence; Speaker recognition; Feature learning; Speech processing; Transfer of learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006937073,0.00110021,0.0005199931,0.0005688542,0.0003149708,0.0005015126,0.001328079,0.0008960766,0.0033956],"category_scores_gemma":[0.001368401,0.0002767024,0.0007235273,0.0004738103,0.0004250345,0.001339797,0.001180443,0.00181245,0.001328198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007994445,"about_ca_system_score_gemma":0.0006822057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006264667,"about_ca_topic_score_gemma":0.01081885,"domain_scores_codex":[0.9997335,0.00005086309,0.00001185409,0.00008975715,0.00005694354,0.00005715092],"domain_scores_gemma":[0.9996619,0.0001362821,0.00002965703,0.0000715921,0.00007265012,0.00002781902],"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":[0.0004038292,0.0003624244,0.002449899,0.000187501,0.0001572165,0.0001725723,0.0001592584,0.204298,0.07347737,0.008133707,0.009022817,0.7011755],"study_design_scores_gemma":[0.00001618688,0.0001180794,0.00110158,0.00001811735,0.00005049158,0.00007828639,0.00001709129,0.9715372,0.01681403,0.007102669,0.003127646,0.00001859227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07080113,0.003363093,0.9149412,0.0006228345,0.0003072948,0.00008242283,0.0003533437,0.005443691,0.004085009],"genre_scores_gemma":[0.8431839,0.001312637,0.1452521,0.0005732206,0.0002104251,0.0001259184,0.0008717959,0.0002237042,0.008246378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006264667,"threshold_uncertainty_score":0.01245636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09106019514806173,"score_gpt":0.3225803774889449,"score_spread":0.2315201823408831,"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."}}