{"id":"W3097523643","doi":"10.3390/app10217522","title":"Robust Deep Speaker Recognition: Learning Latent Representation with Joint Angular Margin Loss","year":2020,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Softmax function; Speaker recognition; Speech recognition; Artificial intelligence; Biometrics; TIMIT; Pattern recognition (psychology); Codebook; Machine learning; Convolutional neural network; Hidden Markov model","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":[0.001709817,0.001090629,0.0007875474,0.0005511062,0.0002875394,0.0007092381,0.001646511,0.0008116737,0.002934003],"category_scores_gemma":[0.002397708,0.0004030166,0.0009334503,0.0005659636,0.0005436681,0.001574855,0.001496621,0.002195528,0.0014995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008379655,"about_ca_system_score_gemma":0.001116468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005010077,"about_ca_topic_score_gemma":0.006360719,"domain_scores_codex":[0.9993488,0.0001834228,0.00002851976,0.0001722094,0.0001827421,0.00008436428],"domain_scores_gemma":[0.9994394,0.0001931788,0.00006902609,0.0001139744,0.0001490008,0.00003533033],"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":[0.0005603814,0.0002552237,0.001555888,0.0001141732,0.000191742,0.00009054548,0.00008706519,0.3797732,0.01686379,0.01005139,0.01073275,0.5797239],"study_design_scores_gemma":[0.000006344939,0.00003111007,0.0001787482,0.000006034473,0.00001106026,0.00001846666,0.000005405347,0.9940142,0.003088512,0.00197959,0.0006535679,0.000006956003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02910052,0.0007233562,0.9644457,0.000267983,0.0001103751,0.00005628652,0.0002364739,0.002599691,0.002459517],"genre_scores_gemma":[0.7157832,0.0008539612,0.2597373,0.0004985212,0.0001714123,0.0001952563,0.002381889,0.0004568885,0.01992158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005010077,"threshold_uncertainty_score":0.009961784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1056419227313543,"score_gpt":0.2373883588161174,"score_spread":0.1317464360847631,"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."}}