{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002536731,0.0002238719,0.0002153958,0.0001844398,0.0001782848,0.0001743024,0.0003392177,0.0001769184,0.00002930633],"category_scores_gemma":[0.00004090808,0.0001675424,0.0001646266,0.00008331559,0.00006890068,0.000344966,0.00003113548,0.0002025632,0.000005626686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003566462,"about_ca_system_score_gemma":0.00006436207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001151185,"about_ca_topic_score_gemma":0.00001308571,"domain_scores_codex":[0.9988272,0.00002379289,0.0003544472,0.0003881281,0.000278069,0.0001284056],"domain_scores_gemma":[0.9987727,0.0003258041,0.0002931585,0.0003759113,0.0002107703,0.00002164839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001099957,0.00004052838,0.00005021957,0.0001379709,0.00004332569,7.118445e-7,0.0002290621,0.00006790204,0.003713222,0.08498433,0.0008419932,0.9097807],"study_design_scores_gemma":[0.001742537,0.00105518,0.001984955,0.002835574,0.0002965834,0.000008309367,0.000004600723,0.1489151,0.297119,0.1794382,0.3649865,0.001613396],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002817051,0.0002283208,0.9719964,0.001324529,0.0001800374,0.0009140065,0.00006878225,0.0001560353,0.02485023],"genre_scores_gemma":[0.3137612,0.0004973689,0.4247268,0.002700336,0.000536704,0.0003066837,0.001398222,0.0002085875,0.2558641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9081674,"threshold_uncertainty_score":0.6832182,"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."}}