{"id":"W1600530438","doi":"10.1007/978-3-642-03658-3_110","title":"Using Avatars for Improving Speaker Identification in Captioning","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Subtitles and Audiovisual Media","field":"Arts and Humanities","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Closed captioning; Computer science; Avatar; Identification (biology); Speaker identification; Multimedia; Speech recognition; Citizen journalism; Human–computer interaction; Natural language processing; World Wide Web; Artificial intelligence; Speaker recognition; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001208174,0.001520478,0.0009413729,0.0006706515,0.0005663505,0.001589454,0.0009895383,0.00151565,0.02277619],"category_scores_gemma":[0.006527464,0.0004680677,0.0005790353,0.0004502459,0.0003714642,0.00267318,0.001680036,0.00143363,0.01060478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001953148,"about_ca_system_score_gemma":0.0001809955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003370608,"about_ca_topic_score_gemma":0.0004613782,"domain_scores_codex":[0.9988495,0.0004868219,0.00004877506,0.0002767971,0.0002491732,0.00008882518],"domain_scores_gemma":[0.9970474,0.001299656,0.0001267161,0.0003146201,0.001078919,0.0001327781],"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":[0.00162779,0.0001909945,0.0006712309,0.000795849,0.00005868507,0.0004169779,0.0007598018,0.006261088,0.3069313,0.002760449,0.01387303,0.6656528],"study_design_scores_gemma":[0.0001352404,0.001339363,0.003069146,0.0002858607,0.0003122502,0.00221379,0.001309415,0.4628929,0.4750546,0.0054803,0.04777182,0.0001353285],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08644617,0.001685512,0.8759754,0.0004801713,0.001786263,0.0003419588,0.0007666796,0.01197164,0.02054624],"genre_scores_gemma":[0.3739478,0.001344767,0.5981658,0.0003451716,0.0006752458,0.0003717017,0.002199531,0.002169986,0.02078008],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02277619,"threshold_uncertainty_score":0.07619393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06586589965452995,"score_gpt":0.2796431986847472,"score_spread":0.2137772990302173,"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."}}