{"id":"W2110686509","doi":"10.1109/icassp.2006.1660091","title":"A Dempster-Shafer Based Fusion Approach for Audio-Visual Speech Recognition with Application to Large Vocabulary French Speech","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Audio mining; Vocabulary; Dempster–Shafer theory; Artificial intelligence; Audio visual; Context (archaeology); Sensor fusion; Natural language processing; Speech processing; Voice activity detection; 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":[0.0004921674,0.000259968,0.0002321134,0.0002314469,0.0002828022,0.0002725112,0.0004928344,0.0001267067,0.00003004934],"category_scores_gemma":[0.00002045796,0.0002139885,0.00007452634,0.000850831,0.00002076183,0.0005691963,0.0001161687,0.0001220627,0.00008647394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007527611,"about_ca_system_score_gemma":0.0001196016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001022782,"about_ca_topic_score_gemma":0.0001142456,"domain_scores_codex":[0.9978151,0.00003881498,0.0003185338,0.0008325387,0.0004478452,0.0005471788],"domain_scores_gemma":[0.9989367,0.00005999319,0.0001304903,0.0004513055,0.0002803174,0.0001411514],"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":[0.0001534238,0.001444217,0.006380928,0.0002415791,0.00002635908,0.000019845,0.0001253739,0.0004628925,0.05978524,0.0002894523,0.01227728,0.9187934],"study_design_scores_gemma":[0.002531474,0.0006091067,0.005362503,0.00008937601,0.00003600805,0.00006551564,0.00004241622,0.2546904,0.7277609,0.002576607,0.005361745,0.0008739861],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07627808,0.00002998229,0.9173128,0.0005447973,0.0000524427,0.001021698,0.00001059222,0.00036103,0.004388549],"genre_scores_gemma":[0.3290696,4.96539e-7,0.668746,0.001065775,0.0001975561,0.0002237573,0.0001942024,0.00002175328,0.0004808893],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9179194,"threshold_uncertainty_score":0.8726199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01124640559120327,"score_gpt":0.242137145903523,"score_spread":0.2308907403123197,"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."}}