{"id":"https://openalex.org/W2677604782","doi":"https://doi.org/10.1109/icassp.2017.7952674","title":"Bayesian joint-sequence models for grapheme-to-phoneme conversion","display_name":"Bayesian joint-sequence models for grapheme-to-phoneme conversion","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2677604782","doi":"https://doi.org/10.1109/icassp.2017.7952674","mag":"2677604782"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110926453","display_name":"Mirko Hannemann","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"funder","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"funder","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ","DE"],"is_corresponding":false,"raw_author_name":"Mirko Hannemann","raw_affiliation_strings":["HLT, RWTH Aachen, Germany","Speech@FIT, Brno University of Technology, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"HLT, RWTH Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017882589","display_name":"Jan Trmal","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"funder","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Trmal","raw_affiliation_strings":["[CLSP, Johns Hopkins University, Baltimore, MD, USA]"],"affiliations":[{"raw_affiliation_string":"[CLSP, Johns Hopkins University, Baltimore, MD, USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104831405","display_name":"Lucas Ondel","orcid":"https://orcid.org/0000-0003-4512-0471"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"funder","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lucas Ondel","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czech Republic#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czech Republic#TAB#","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008468618","display_name":"Santosh Kesiraju","orcid":"https://orcid.org/0000-0002-3725-742X"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Santosh Kesiraju","raw_affiliation_strings":["IIIT-Hyderabad, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IIIT-Hyderabad, India#TAB#","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"funder","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czech Republic#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czech Republic#TAB#","institution_ids":["https://openalex.org/I60587646"]}]}],"institution_assertions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":8,"citation_normalized_percentile":{"value":0.86973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":83,"max":84},"biblio":{"volume":null,"issue":null,"first_page":"2836","last_page":"2840"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9999,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9999,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9996,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6489364},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.60865766},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5526222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705616},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6489364},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.60865766},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5845167},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5526222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4578802},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43950373},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34330112},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://hal.science/hal-03478209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-03478209","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":22,"referenced_works":["https://openalex.org/W1551893515","https://openalex.org/W157259314","https://openalex.org/W1593247906","https://openalex.org/W1916501714","https://openalex.org/W2005902041","https://openalex.org/W2087309226","https://openalex.org/W2087739751","https://openalex.org/W2090755665","https://openalex.org/W2099964107","https://openalex.org/W2107240889","https://openalex.org/W2140991203","https://openalex.org/W2154099718","https://openalex.org/W2159399018","https://openalex.org/W2170353620","https://openalex.org/W2251711535","https://openalex.org/W2262393948","https://openalex.org/W2293770964","https://openalex.org/W2295592722","https://openalex.org/W2397041158","https://openalex.org/W2405962136","https://openalex.org/W4299619505","https://openalex.org/W88183020"],"related_works":["https://openalex.org/W4385893898","https://openalex.org/W4285757703","https://openalex.org/W2610662399","https://openalex.org/W2509341624","https://openalex.org/W2506515307","https://openalex.org/W2383836440","https://openalex.org/W2136542423","https://openalex.org/W2060656088","https://openalex.org/W2045966063","https://openalex.org/W1972594981"],"abstract_inverted_index":{"We":[0,102],"describe":[1],"a":[2,38,42,107,130,143],"fully":[3],"Bayesian":[4,39,144],"approach":[5,40],"to":[6,28,51,55,117],"grapheme-to-phoneme":[7],"conversion":[8],"based":[9],"on":[10,106],"the":[11,73,79,99,118],"joint-sequence":[12],"model":[13,29,105,138],"(JSM).":[14],"Usually,":[15],"standard":[16,96,108],"smoothed":[17,80,121],"n-gram":[18],"language":[19],"models":[20],"(LM,":[21],"e.g.":[22],"Kneser-Ney)":[23],"are":[24,82],"used":[25,77,141],"with":[26,95],"JSMs":[27,122],"graphone":[30],"sequences":[31],"(joint":[32],"grapheme-phoneme":[33],"pairs).":[34],"However,":[35],"we":[36],"take":[37],"using":[41,52],"hierarchical":[43],"Pitman-Yor-Process":[44],"LM.":[45],"This":[46],"provides":[47],"an":[48],"elegant":[49],"alternative":[50],"smoothing":[53],"techniques":[54],"avoid":[56],"over-training.":[57],"No":[58],"held-out":[59],"sets":[60],"and":[61,67,93,146],"complex":[62],"parameter":[63],"tuning":[64],"is":[65,86],"necessary,":[66],"several":[68],"convergence":[69],"problems":[70],"encountered":[71],"in":[72,78,123,142],"discounted":[74],"Expectation-Maximization":[75],"(as":[76],"JSMs)":[81],"avoided.":[83],"Every":[84],"step":[85],"modeled":[87],"by":[88],"weighted":[89],"finite":[90],"state":[91],"transducers":[92],"implemented":[94],"operations":[97],"from":[98],"OpenFST":[100],"toolkit.":[101],"evaluate":[103],"our":[104,137],"data":[109],"set":[110],"(CMUdict),":[111],"where":[112],"it":[113],"gives":[114],"comparable":[115],"results":[116],"previously":[119],"reported":[120],"terms":[124],"of":[125],"phoneme-error":[126],"rate":[127],"while":[128],"requiring":[129],"much":[131],"smaller":[132],"training/testing":[133],"time.":[134],"Most":[135],"importantly,":[136],"can":[139],"be":[140],"framework":[145],"for":[147],"(partly)":[148],"un-supervised":[149],"training.":[150]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2677604782","counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-04-16T06:44:20.698839","created_date":"2017-06-30"}