{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002113447,0.001980672,0.0008005771,0.00349456,0.001214596,0.002199709,0.002762104,0.001587017,0.02567034],"category_scores_gemma":[0.006289115,0.000825829,0.001449216,0.002029269,0.000792706,0.003011914,0.003930368,0.002891571,0.02648637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009749649,"about_ca_system_score_gemma":0.002640819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007859153,"about_ca_topic_score_gemma":0.01769631,"domain_scores_codex":[0.9978774,0.0005273949,0.000136448,0.0008569817,0.0004275212,0.000174358],"domain_scores_gemma":[0.9974149,0.0008894139,0.0001339164,0.0009617238,0.0004542758,0.0001456492],"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":[0.0002855806,0.0001962554,0.001666432,0.0006081467,0.0000815471,0.0002181777,0.0003976905,0.00468395,0.02853047,0.007719212,0.09935314,0.8562593],"study_design_scores_gemma":[0.0002206426,0.0003830311,0.009414364,0.0002792176,0.0001297892,0.0009093597,0.000729365,0.558128,0.101463,0.04382316,0.2842852,0.0002348357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009649545,0.0005192821,0.8544203,0.0004116919,0.0003516139,0.0004226365,0.01975865,0.1071389,0.007327385],"genre_scores_gemma":[0.05935929,0.0002860606,0.854714,0.0002793352,0.0001671553,0.001108452,0.07065373,0.005433739,0.007998261],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02567034,"threshold_uncertainty_score":0.08587587,"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."}}