{"id":"W4412042445","doi":"10.1007/978-3-031-85747-8_9","title":"On the Use of Cross-Attentive Fusion Techniques for Audio-Visual Speaker Verification","year":2025,"lang":"en","type":"book-chapter","venue":"Machine translation","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Audio visual; Speaker verification; Artificial intelligence; Computational linguistics; Natural language processing; Fusion; Speaker recognition; Linguistics; 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":[0.001302399,0.0008983518,0.0007447578,0.0008552876,0.0004288995,0.001181169,0.001123661,0.001142087,0.006708933],"category_scores_gemma":[0.001965848,0.0004446274,0.0007373365,0.001079756,0.0006770319,0.001811787,0.001600827,0.001148303,0.004169096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000244135,"about_ca_system_score_gemma":0.0002322323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001205688,"about_ca_topic_score_gemma":0.002052496,"domain_scores_codex":[0.9993079,0.0001784262,0.00003853692,0.0001351317,0.0002867843,0.0000533317],"domain_scores_gemma":[0.9991394,0.0005196778,0.00003030694,0.0001215824,0.0001756501,0.00001334086],"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":[0.000160639,0.00004996569,0.0001481537,0.0001744772,0.00007334723,0.0001211723,0.0001078166,0.01190636,0.07328983,0.01563827,0.005001351,0.8933287],"study_design_scores_gemma":[0.00002207547,0.0002959392,0.002115979,0.0001651415,0.000185637,0.001819724,0.0001380591,0.6881276,0.2201248,0.04360671,0.0432951,0.0001032361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002605316,0.00362954,0.9866231,0.00006991908,0.0001254587,0.00002749605,0.00003735553,0.001027399,0.005854385],"genre_scores_gemma":[0.1337447,0.007500556,0.8310773,0.0003370854,0.0003550766,0.00008075335,0.0005243953,0.0005391713,0.02584091],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006708933,"threshold_uncertainty_score":0.02244359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0605907766277319,"score_gpt":0.3144751265767557,"score_spread":0.2538843499490239,"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."}}