{"id":"W4402625500","doi":"10.1007/s00034-024-02854-4","title":"Attentive Context-Aware Deep Speaker Representations for Voice Biometrics in Adverse Conditions","year":2024,"lang":"en","type":"article","venue":"Circuits Systems and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biometrics; Speech recognition; Speaker recognition; Context (archaeology); Computer science; Voice analysis; Psychology; Artificial intelligence; History","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003521796,0.000124823,0.0001896781,0.0006192221,0.0002323509,0.0005733666,0.0001657307,0.0000731882,0.00001379651],"category_scores_gemma":[0.00006923141,0.000117161,0.0000626547,0.001228306,0.00005338834,0.0008000616,0.00003235144,0.00009688186,0.00003099051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005638213,"about_ca_system_score_gemma":0.0001020533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000369357,"about_ca_topic_score_gemma":0.00002156869,"domain_scores_codex":[0.9987646,0.00005781778,0.0003243222,0.0004405446,0.0001889338,0.0002237549],"domain_scores_gemma":[0.9991015,0.0004201792,0.00007535392,0.000114341,0.0001966663,0.00009196594],"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":[0.000004678458,0.0001287523,0.001387204,0.00160955,0.00008408428,0.0002103047,0.005115718,0.0001523976,0.003399604,0.01563982,0.0008103539,0.9714575],"study_design_scores_gemma":[0.0009849347,0.00008184709,0.004476328,0.001938294,0.00007002285,0.0003383408,0.008758465,0.9682887,0.00100296,0.004648185,0.008770452,0.0006414689],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01519354,0.004213762,0.9772144,0.0003263931,0.0004218192,0.0005498988,0.00005245474,0.0001832924,0.001844425],"genre_scores_gemma":[0.9987756,0.00001457791,0.000483454,0.0001203927,0.00009545831,0.0001258928,0.00001603666,0.00001291273,0.0003556576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9835821,"threshold_uncertainty_score":0.5528988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0477318777086807,"score_gpt":0.3018899819064956,"score_spread":0.2541581041978149,"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."}}