{"id":"W4408355320","doi":"10.1109/icassp49660.2025.10888977","title":"LAVViT: Latent Audio-Visual Vision Transformers for Speaker Verification","year":2025,"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","keywords":"Computer science; Audio visual; Transformer; Speech recognition; Speaker verification; Computer vision; Artificial intelligence; Speaker recognition; Multimedia; Engineering; Electrical engineering","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":[0.0001996065,0.00007477209,0.00008905461,0.0001104842,0.0000923679,0.00009190218,0.0001802774,0.00004962497,0.0001081127],"category_scores_gemma":[0.000025077,0.00006250135,0.00008699657,0.0002382899,0.00001565868,0.0002426456,0.00001729454,0.00003492104,0.0001021545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003098527,"about_ca_system_score_gemma":0.00003974968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008906709,"about_ca_topic_score_gemma":0.00001258036,"domain_scores_codex":[0.9993261,0.00001993164,0.0001560693,0.0002399786,0.0001123033,0.0001456178],"domain_scores_gemma":[0.999659,0.00008299234,0.00002246233,0.0001234758,0.00006983351,0.00004225467],"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":[0.00001413155,0.0000744845,0.00008489001,0.000014679,0.00001520959,4.007529e-7,0.00005529121,0.000001410647,0.003701545,0.02321948,0.005571228,0.9672472],"study_design_scores_gemma":[0.002185112,0.0003147776,0.02303667,0.0001053205,0.00004884238,0.000007692414,0.0001728769,0.3613547,0.3236153,0.0102753,0.2782876,0.0005957183],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006133846,0.00001580078,0.9614778,0.004682555,0.0003199661,0.0002540336,0.000001819403,0.0001516301,0.02696262],"genre_scores_gemma":[0.882796,0.00005374269,0.1049352,0.002105883,0.0000328483,0.00008313143,0.00001224616,0.000008082861,0.009972888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9666516,"threshold_uncertainty_score":0.2548731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01425759948865119,"score_gpt":0.30255972333916,"score_spread":0.2883021238505089,"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."}}