{"id":"W4375869393","doi":"10.1109/icassp49357.2023.10096040","title":"Hybrid Neural Network with Cross- and Self-Module Attention Pooling for Text-Independent Speaker Verification","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Pooling; Time delay neural network; Artificial neural network; Artificial intelligence; Speech recognition; Feature extraction; Pattern recognition (psychology); Convolutional neural network; Hybrid neural network; Neocognitron; Speaker recognition","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":[],"consensus_categories":[],"category_scores_codex":[0.0003127419,0.00009193131,0.000090504,0.00006330125,0.0001980136,0.0003226104,0.0001632855,0.00002717706,0.00002073704],"category_scores_gemma":[0.00001648104,0.00007502698,0.00003797544,0.0002104549,0.00001772476,0.0003737413,0.00005470493,0.00004450448,0.00008383154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000179524,"about_ca_system_score_gemma":0.00001525717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009161916,"about_ca_topic_score_gemma":0.00001176405,"domain_scores_codex":[0.9990904,0.00002350555,0.0001414371,0.0003359726,0.0001714071,0.0002372179],"domain_scores_gemma":[0.999504,0.00008159827,0.00005431367,0.0002087727,0.00008617932,0.00006509873],"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":[0.0001707541,0.0003574609,0.07799982,0.0001657188,0.0002314614,0.00006810511,0.0005092293,0.00455365,0.002673887,0.05012043,0.01175012,0.8513994],"study_design_scores_gemma":[0.0005597014,0.00007858961,0.2190588,0.00001522564,0.00001296797,0.00005941007,0.00002467685,0.7738512,0.001869771,0.002257387,0.002010914,0.0002013851],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.663661,0.00001311984,0.3334747,0.0006339673,0.0002504879,0.0002851498,0.000002630369,0.0005472661,0.001131717],"genre_scores_gemma":[0.9455224,0.00001362032,0.05320008,0.0002123726,0.00010733,0.00004520244,0.00001476214,0.00001115477,0.0008730798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.851198,"threshold_uncertainty_score":0.311094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02065617132976316,"score_gpt":0.2586632693625301,"score_spread":0.238007098032767,"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."}}