{"id":"W4387800211","doi":"10.48550/arxiv.2310.11541","title":"MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Syllabification; Computer science; Natural language processing; Artificial intelligence; Representation (politics); Speech recognition; Stress (linguistics); Linguistics; Syllable","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004338514,0.0002013088,0.0002616597,0.0004843767,0.000150199,0.0001672888,0.0003784846,0.0002257458,0.00000843352],"category_scores_gemma":[0.0003348245,0.0002494504,0.00006859455,0.0005274633,0.00008479218,0.0002059986,0.0005011921,0.000327817,0.00002998418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008202541,"about_ca_system_score_gemma":0.00006797173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002676089,"about_ca_topic_score_gemma":0.0004830136,"domain_scores_codex":[0.9982879,0.0001785165,0.0002217911,0.0009995248,0.00007764819,0.0002345906],"domain_scores_gemma":[0.9986612,0.000454941,0.0002023144,0.0004493546,0.0001301061,0.0001021287],"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":[0.000785174,0.001251669,0.1465065,0.002085289,0.0006705339,0.001275053,0.02051693,0.1347243,0.01064974,0.08305144,0.0007467884,0.5977366],"study_design_scores_gemma":[0.002180912,0.00006217448,0.04414771,0.0002533499,0.00007711214,0.00001745776,0.001457218,0.9268414,0.001480096,0.0221739,0.0005958805,0.0007127861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6825289,0.00002621437,0.3161521,0.0001359932,0.000174293,0.0006098093,0.000007858695,0.0001909808,0.0001738938],"genre_scores_gemma":[0.9717122,0.0004403197,0.02476645,0.00002783093,0.00003641195,0.000008862894,0.00004363477,0.00002177761,0.002942455],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7921171,"threshold_uncertainty_score":0.9999958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2157484087785792,"score_gpt":0.2591463813066213,"score_spread":0.04339797252804206,"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."}}