{"id":"W2125572892","doi":"10.1109/ispa.2003.1296393","title":"Acoustic speech to lip feature mapping for multimedia applications","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Speech recognition; Hidden Markov model; Computer science; Feature extraction; Feature (linguistics); Acoustic model; Viseme; Speech processing; Artificial intelligence; Pattern recognition (psychology)","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":[0.00008732848,0.00008976181,0.00008652757,0.00008463529,0.00015267,0.0001571916,0.0005163622,0.00004785094,0.000005195801],"category_scores_gemma":[0.00004432561,0.00007864849,0.0000385105,0.0004507708,0.000008506306,0.0002034993,0.00009230179,0.00006658005,0.000143112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004462661,"about_ca_system_score_gemma":0.00008189113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004978298,"about_ca_topic_score_gemma":0.00002677924,"domain_scores_codex":[0.9992241,0.000002662911,0.00009310232,0.0003022896,0.0001237671,0.000254075],"domain_scores_gemma":[0.9994152,0.00004677089,0.00002908462,0.0002955956,0.0000859268,0.0001274851],"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":[0.000003410788,0.00009463293,0.00007128143,0.00006876383,0.00001408234,0.000005851427,0.0008079263,0.002432782,0.1188631,0.002856096,0.006681747,0.8681003],"study_design_scores_gemma":[0.001630942,0.0001334286,0.0009402211,0.0001274499,0.00001576227,0.00005230668,0.0002962884,0.01789811,0.8075638,0.03152786,0.1389895,0.0008242635],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00117597,0.00004890702,0.989893,0.006663514,0.000107366,0.0004614347,0.000001908554,0.0002599678,0.00138795],"genre_scores_gemma":[0.06430568,0.000001584614,0.9325417,0.001844767,0.0001969744,0.0001444081,0.000002594055,0.00000720703,0.0009551244],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8672761,"threshold_uncertainty_score":0.3207192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01641891270849392,"score_gpt":0.2644864221848932,"score_spread":0.2480675094763992,"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."}}