{"id":"W4283818626","doi":"10.1609/aaai.v36i2.20102","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Leverage (statistics); Speech recognition; Synchronization (alternating current); Visualization; Artificial intelligence; Sound quality; Audio visual; Representation (politics); Face (sociological concept); Computer vision; Multimedia; Channel (broadcasting)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007938362,0.0003143403,0.0003148079,0.0001891749,0.001002516,0.0004999971,0.002331966,0.00006407281,0.0001211872],"category_scores_gemma":[0.000185384,0.0002459309,0.0001083203,0.001180161,0.0001911227,0.0008815199,0.000881904,0.0005537141,0.00003319046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001571962,"about_ca_system_score_gemma":0.0002298807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003463538,"about_ca_topic_score_gemma":0.00001199122,"domain_scores_codex":[0.9970704,0.00003962377,0.000556791,0.0007771912,0.001053161,0.0005027855],"domain_scores_gemma":[0.9983081,0.00006829525,0.0006203408,0.0003964318,0.0004918418,0.0001149686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001056339,0.0002177992,0.0002482994,0.00007265152,0.0000352541,0.000005425434,0.004904864,0.005576788,0.625535,0.02922842,0.000232113,0.3338378],"study_design_scores_gemma":[0.00004421955,0.0002953182,0.00004140847,0.0001333772,0.00001581437,0.00005503454,0.001155835,0.1167503,0.8715265,0.009585097,0.00007934584,0.0003177139],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6947783,0.0001268955,0.2899028,0.004024602,0.001012931,0.0008945751,0.000007032699,0.0003103406,0.00894253],"genre_scores_gemma":[0.9893633,0.00001236832,0.009641468,0.0002914218,0.0001343536,0.00009161944,0.000001235669,0.00002440025,0.0004398728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3335201,"threshold_uncertainty_score":0.9999993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05082625186549095,"score_gpt":0.260706983795317,"score_spread":0.209880731929826,"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."}}