{"id":"W4388878581","doi":"10.1007/978-3-031-48312-7_2","title":"Audio-Visual Speaker Verification via Joint Cross-Attention","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Leverage (statistics); Modal; Speech recognition; Audio visual; Concatenation (mathematics); Feature (linguistics); Artificial intelligence; Joint (building); Modalities; Pattern recognition (psychology); Multimedia","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":[0.001319578,0.001563763,0.001548513,0.001042011,0.0005719044,0.001403519,0.001343198,0.001632496,0.01198305],"category_scores_gemma":[0.002059116,0.0006013082,0.001141146,0.0008467798,0.0003722702,0.001601923,0.002899003,0.001212291,0.01029795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003096404,"about_ca_system_score_gemma":0.0008053589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002202358,"about_ca_topic_score_gemma":0.005119693,"domain_scores_codex":[0.9988141,0.0002087365,0.00006181163,0.0003156432,0.0004035329,0.0001962675],"domain_scores_gemma":[0.9989667,0.0004192505,0.00005339912,0.0001983144,0.0003056837,0.00005674855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008042855,0.0001155987,0.0003554427,0.0001687502,0.0001260695,0.0001771471,0.00004761443,0.004065386,0.2373991,0.001232068,0.004106442,0.751402],"study_design_scores_gemma":[0.0001065017,0.0003367918,0.005974334,0.00005961568,0.0003493421,0.001576413,0.0001097239,0.5951003,0.3817219,0.004368343,0.01021115,0.00008562337],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02035768,0.001771764,0.9633743,0.0001622154,0.000419945,0.0001091177,0.0003251791,0.005199218,0.008280398],"genre_scores_gemma":[0.3729017,0.001614122,0.5934072,0.0005720419,0.0004190128,0.0001841222,0.001827794,0.0009309096,0.02814311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01198305,"threshold_uncertainty_score":0.04008722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02622826901695002,"score_gpt":0.2813863992700888,"score_spread":0.2551581302531388,"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."}}