{"id":"W4382053133","doi":"10.1109/iwbf57495.2023.10157564","title":"On the Use of Cross-module Attention Statistics Pooling for Speaker Verification","year":2023,"lang":"en","type":"article","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","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Pooling; Artificial neural network; Speech recognition; Artificial intelligence; Time delay neural network; Feature extraction; Pattern recognition (psychology); Convolutional neural network; Speaker recognition","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":[0.00157894,0.0008595487,0.0005823117,0.000595556,0.0003473155,0.0006072292,0.001109747,0.000791522,0.002362175],"category_scores_gemma":[0.001532731,0.0003482531,0.0005439265,0.000477918,0.000417463,0.001483979,0.001303431,0.0008003372,0.0008947618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005056886,"about_ca_system_score_gemma":0.0006349155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005245657,"about_ca_topic_score_gemma":0.008106082,"domain_scores_codex":[0.9994305,0.0001486797,0.00002693426,0.0002107051,0.0001114134,0.00007174673],"domain_scores_gemma":[0.9994656,0.0001660649,0.00004030649,0.0001219091,0.0001803764,0.0000257334],"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":[0.0007049005,0.0001641295,0.002470041,0.0001106466,0.0002890264,0.0002152871,0.0001520387,0.04128028,0.154034,0.004464003,0.002611103,0.7935045],"study_design_scores_gemma":[0.00001918302,0.0002529514,0.003494415,0.00001824518,0.0001283424,0.0002220949,0.00003516989,0.8946394,0.09503175,0.002666523,0.003458851,0.00003305493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06119935,0.001015607,0.930622,0.0001694385,0.0001105566,0.00008816077,0.0001133921,0.003247318,0.003434212],"genre_scores_gemma":[0.8110098,0.0004966238,0.1808609,0.0003258211,0.00007363405,0.00006263512,0.0004581049,0.0001295704,0.006582941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005245657,"threshold_uncertainty_score":0.01043022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1666763134449241,"score_gpt":0.3312485794147502,"score_spread":0.1645722659698261,"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."}}