{"id":"W4378231186","doi":"10.1007/s10772-023-10030-3","title":"Mouth2Audio: intelligible audio synthesis from videos with distinctive vowel articulation","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Simon Fraser University","keywords":"Computer science; Speech recognition; Formant; Spectrogram; Manner of articulation; Landmark; Vowel; Articulation (sociology); Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002850462,0.0001508924,0.0002441568,0.001001964,0.00007070367,0.0001680979,0.001462999,0.0001207214,0.00003973979],"category_scores_gemma":[0.0004870816,0.0001187052,0.0000817923,0.0009942516,0.0001155443,0.0006971493,0.0002668372,0.0003153616,0.0001476147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001441806,"about_ca_system_score_gemma":0.0001196487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002302739,"about_ca_topic_score_gemma":0.00002149561,"domain_scores_codex":[0.9983831,0.00002504579,0.0004421145,0.0002660478,0.0006442301,0.0002394323],"domain_scores_gemma":[0.9981897,0.0002344537,0.0005034496,0.0002493322,0.0007569366,0.00006616097],"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":[0.0001587786,0.0001157999,0.01938266,0.000006945577,0.0005636278,0.001914331,0.0005799265,0.000857681,0.04748267,0.002747024,0.001304133,0.9248864],"study_design_scores_gemma":[0.0005555872,0.0001659148,0.009741265,0.0002847901,0.00003345281,0.0007839574,0.0003086752,0.003262282,0.9078937,0.07458425,0.002147195,0.0002389387],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6299495,0.0001052573,0.3529836,0.01555821,0.000686691,0.00006583567,0.000008379939,0.0002979674,0.0003444795],"genre_scores_gemma":[0.9127269,0.00004541699,0.08674057,0.0001129681,0.0002553866,0.000006857828,0.000002904837,0.00001296673,0.00009603897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9246475,"threshold_uncertainty_score":0.4840658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009332505270161847,"score_gpt":0.2516490338928938,"score_spread":0.242316528622732,"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."}}