{"id":"W3037446006","doi":"10.18653/v1/2020.sigmorphon-1.16","title":"One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Grapheme; Transformer; Computer science; Word error rate; Task (project management); Speech recognition; Artificial intelligence; Language model; Natural language processing; Speech synthesis; Engineering; Voltage","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008167754,0.001883888,0.0008794165,0.0006402968,0.0005540882,0.001171969,0.001673365,0.00109434,0.005180701],"category_scores_gemma":[0.001647178,0.0005187725,0.001206903,0.0005945505,0.0005182333,0.002618209,0.00179691,0.003419038,0.005621825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000427006,"about_ca_system_score_gemma":0.001011296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005381078,"about_ca_topic_score_gemma":0.01061553,"domain_scores_codex":[0.9995371,0.0001008169,0.00001992876,0.00021533,0.00007044206,0.00005640236],"domain_scores_gemma":[0.9994524,0.0001576034,0.00002385336,0.0001684774,0.000138893,0.00005878671],"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":[0.0008704458,0.000488148,0.003518271,0.0002586203,0.0005371459,0.0007642509,0.0005145982,0.1814153,0.04430095,0.01586074,0.04377837,0.7076932],"study_design_scores_gemma":[0.00004107754,0.0001096319,0.0004259448,0.00002055624,0.0001323129,0.0002752885,0.00009840204,0.960033,0.01505354,0.01544716,0.008321952,0.0000410918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05921626,0.001081249,0.9049506,0.0014689,0.0009304585,0.0001132098,0.001484315,0.01950455,0.01125049],"genre_scores_gemma":[0.7270693,0.0008126764,0.2393166,0.00109692,0.00034078,0.0001728958,0.005146155,0.001991995,0.02405257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005381078,"threshold_uncertainty_score":0.01733112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05299286893416044,"score_gpt":0.2905230790569408,"score_spread":0.2375302101227804,"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."}}