{"id":"W4387211585","doi":"10.1007/978-3-031-43990-2_41","title":"Speech Audio Synthesis from Tagged MRI and Non-negative Matrix Factorization via Plastic Transformer","year":2023,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute on Deafness and Other Communication Disorders; National Cancer Institute; National Institutes of Health","keywords":"Computer science; Spectrogram; Weighting; Speech recognition; Mean opinion score; Artificial intelligence; Pattern recognition (psychology); Metric (unit); Acoustics","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":[0.0004480815,0.0002454433,0.0002648648,0.0004893374,0.0003443212,0.0005785618,0.001100769,0.00009917336,0.000008435402],"category_scores_gemma":[0.0003527799,0.0002112126,0.00004140609,0.003415996,0.0002649604,0.001154468,0.0002363969,0.0002383407,0.00004550448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009161713,"about_ca_system_score_gemma":0.0001817213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008384739,"about_ca_topic_score_gemma":0.00006363567,"domain_scores_codex":[0.9975894,0.00004698228,0.0002744703,0.0009221939,0.0005939067,0.0005730119],"domain_scores_gemma":[0.9978207,0.001449146,0.00009831297,0.0003864833,0.0001000647,0.0001453409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009775102,0.00003091805,0.004419832,0.00003046573,0.00001072347,0.0000552259,0.003839347,0.01690229,0.0791746,0.00001312119,0.00001268623,0.895501],"study_design_scores_gemma":[0.0001934068,0.00004313802,0.01591362,0.00009395122,0.000004299538,0.00001055248,0.000001846229,0.5243023,0.4473325,0.01186088,0.000007567044,0.0002359681],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1580756,0.00003804661,0.8399701,0.0007616053,0.0007947375,0.0001498459,0.000004484843,0.0001950925,0.00001055784],"genre_scores_gemma":[0.6930798,0.00001468444,0.3066106,0.0001558691,0.0001203529,0.000008129417,0.000001324036,0.000008204102,0.000001014004],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.895265,"threshold_uncertainty_score":0.8612999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008987442967171032,"score_gpt":0.2445253613960175,"score_spread":0.2355379184288465,"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."}}