{"id":"W4389519335","doi":"10.18653/v1/2023.emnlp-industry.8","title":"MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Syllabification; Natural language processing; Artificial intelligence; Speech recognition; Representation (politics); 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":[],"consensus_categories":[],"category_scores_codex":[0.0004385368,0.00007896771,0.0001125842,0.0002462551,0.0001039878,0.0001429036,0.0001112038,0.00005558303,0.00001600158],"category_scores_gemma":[0.0004185966,0.0000797892,0.00001988096,0.0005044415,0.00003144704,0.0001858874,0.00006554064,0.00007103138,0.00004487339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001420427,"about_ca_system_score_gemma":0.00001742247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007667156,"about_ca_topic_score_gemma":0.0002160954,"domain_scores_codex":[0.9990994,0.00007372339,0.0001892429,0.0003529972,0.0001178974,0.0001667651],"domain_scores_gemma":[0.9992594,0.000408086,0.00005356499,0.0001656992,0.00005849364,0.00005481618],"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":[0.00001572567,0.00004451345,0.004587799,0.00003144881,0.000008545971,0.000006915225,0.002347962,0.00006155674,0.01595686,0.001984029,0.0001997971,0.9747549],"study_design_scores_gemma":[0.00351405,0.0001225021,0.2249599,0.00008457514,0.00001754892,0.00006125197,0.003995544,0.7148372,0.04077711,0.005483835,0.005549781,0.0005967056],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8565636,0.00002507746,0.1409661,0.0008614067,0.00008679736,0.0004968629,0.000001418543,0.0002618319,0.0007368737],"genre_scores_gemma":[0.8150858,0.0001377434,0.1809316,0.0001093111,0.00003318875,0.00008641622,0.00002145892,0.00001274138,0.003581666],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9741582,"threshold_uncertainty_score":0.3253709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08676770552050438,"score_gpt":0.3358065862145701,"score_spread":0.2490388806940657,"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."}}