{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001957038,0.002073402,0.0007787843,0.003464941,0.001231971,0.002013839,0.002619178,0.001559688,0.02275353],"category_scores_gemma":[0.006190537,0.0007748415,0.00141381,0.001988089,0.0007185774,0.002765612,0.003659392,0.00291701,0.02567469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009557237,"about_ca_system_score_gemma":0.002658923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009582985,"about_ca_topic_score_gemma":0.02191976,"domain_scores_codex":[0.9979637,0.0004702683,0.0001359226,0.0008502281,0.0004039463,0.0001759869],"domain_scores_gemma":[0.9975846,0.0008211014,0.0001320529,0.0008345023,0.0004850693,0.0001426868],"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":[0.0003450816,0.0002338718,0.002413782,0.0006957012,0.00009478907,0.0002552521,0.0004844269,0.005114877,0.03325139,0.006112169,0.1181987,0.8327999],"study_design_scores_gemma":[0.0002498337,0.0004172584,0.01381177,0.0003116561,0.0001516285,0.001033852,0.0009800474,0.5332482,0.1088964,0.03266405,0.3079553,0.0002799494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0151509,0.0006942226,0.8098425,0.0004697815,0.0004763945,0.000596976,0.03614992,0.1272599,0.009359376],"genre_scores_gemma":[0.06751512,0.0003108435,0.8029752,0.0002771018,0.0001632234,0.001386088,0.1141353,0.005217221,0.008019985],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02275353,"threshold_uncertainty_score":0.07611817,"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."}}