{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001136915,0.0008031004,0.0006944342,0.000531404,0.0003155768,0.000469044,0.001190607,0.0008041246,0.002223501],"category_scores_gemma":[0.001116405,0.000355273,0.0005349564,0.0003865512,0.0003016844,0.001449132,0.001161256,0.0008576731,0.0008228183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000620278,"about_ca_system_score_gemma":0.0005860048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005497566,"about_ca_topic_score_gemma":0.008300405,"domain_scores_codex":[0.9995483,0.00008554465,0.00002328768,0.0001620815,0.0001038042,0.00007703112],"domain_scores_gemma":[0.9996417,0.0001128481,0.00003172865,0.00006576235,0.0001268266,0.00002126436],"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":[0.0009432007,0.0002789729,0.001921806,0.0001249689,0.0002945872,0.0002191536,0.0001133462,0.07709844,0.133941,0.002217288,0.004419232,0.778428],"study_design_scores_gemma":[0.00001640366,0.00009366634,0.001262102,0.00000747936,0.00006479624,0.00008201511,0.00001505391,0.9557181,0.04076678,0.0008907884,0.001064811,0.00001809478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1165477,0.00142972,0.8737517,0.0001909195,0.0002082097,0.0001038866,0.0002767001,0.004733898,0.002757173],"genre_scores_gemma":[0.8020406,0.0003167716,0.1898636,0.0002395718,0.0000780394,0.0001032212,0.0008033076,0.0001410484,0.006413883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005497566,"threshold_uncertainty_score":0.01093113,"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."}}