{"id":"W4388380244","doi":"10.1007/s10772-023-10059-4","title":"Attention-based factorized TDNN for a noise-robust and spoof-aware speaker verification system","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Spoofing attack; Speech recognition; Speaker verification; Encoder; Speaker recognition; Artificial neural network; Context (archaeology); Mel-frequency cepstrum; Artificial intelligence; Word error rate; Frame (networking); Pattern recognition (psychology); Feature extraction; Telecommunications","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004611604,0.0001206776,0.0002165888,0.001173589,0.00007047164,0.0001216444,0.0008685119,0.0001488878,0.00001924782],"category_scores_gemma":[0.0002633495,0.0001099089,0.0001263124,0.0004724281,0.00006282541,0.0002712327,0.00008216001,0.0001566538,0.00005577456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000140732,"about_ca_system_score_gemma":0.00009189431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000533599,"about_ca_topic_score_gemma":0.000003883126,"domain_scores_codex":[0.9986997,0.00002797986,0.000464781,0.0002281562,0.0004041685,0.0001751861],"domain_scores_gemma":[0.9982157,0.0001934228,0.0004020664,0.0002019441,0.0009264555,0.00006036548],"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":[0.0002484701,0.0001948172,0.01023126,0.0001068065,0.0004986131,0.0005348059,0.000126955,0.0001115598,0.04920394,0.04741565,0.003613088,0.887714],"study_design_scores_gemma":[0.01849742,0.001511048,0.05176797,0.002071849,0.0002695077,0.007869053,0.003746283,0.5049473,0.2740705,0.03552781,0.09776163,0.001959623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2943845,0.00005611041,0.6832986,0.01892824,0.002364073,0.0002768076,0.00003792006,0.0004654143,0.0001883597],"genre_scores_gemma":[0.9213557,0.0000366927,0.07812569,0.0001034307,0.0001934659,0.00002199406,0.00001199674,0.00001424553,0.0001368013],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8857544,"threshold_uncertainty_score":0.4481954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02756174976548047,"score_gpt":0.2720836184628326,"score_spread":0.2445218686973522,"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."}}