{"id":"W2543194656","doi":"10.1109/have.2004.1391905","title":"Multimodal talker localization in video conferencing environments","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Fonds Wetenschappelijk Onderzoek","keywords":"Computer science; Modality (human–computer interaction); Modular design; Architecture; Computer vision; Artificial intelligence; Sensor fusion; Modalities; Videoconferencing; 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":[0.00008777338,0.00006188255,0.00006005508,0.00005825239,0.00003935987,0.00007400025,0.0002060872,0.0000311183,0.00007106447],"category_scores_gemma":[0.00001293303,0.00005584906,0.0000124071,0.0001241827,0.00001225093,0.0005960637,0.00007600587,0.00004849962,0.0001466782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005137141,"about_ca_system_score_gemma":0.00002075742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002537983,"about_ca_topic_score_gemma":0.00005179503,"domain_scores_codex":[0.999384,0.00001335072,0.0001258389,0.0001906502,0.0001281554,0.0001579573],"domain_scores_gemma":[0.9997785,0.0000122643,0.00002794219,0.0001363695,0.000005699721,0.00003919388],"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":[0.000004170286,0.0001656,0.04059683,0.000009651324,0.000005715667,0.00001343758,0.001309114,0.02104217,0.03116722,0.002506505,0.0005455097,0.9026341],"study_design_scores_gemma":[0.0005110416,0.00001358493,0.009103538,0.00002050298,8.364158e-7,0.000004316158,0.00002930608,0.661853,0.3199595,0.000536705,0.007811644,0.000156108],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05427902,0.0000356458,0.9402451,0.0005118434,0.00003848681,0.00004516719,8.200701e-8,0.00004931015,0.004795379],"genre_scores_gemma":[0.9139829,0.000004701972,0.08462866,0.0009822414,0.00002880001,0.000002646466,9.068123e-7,0.000003032918,0.0003661545],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.902478,"threshold_uncertainty_score":0.2277459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01013697115240418,"score_gpt":0.2277007491503946,"score_spread":0.2175637779979905,"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."}}