{"id":"https://openalex.org/W2748157908","doi":"https://doi.org/10.21437/interspeech.2017-1436","title":"Multitask Sequence-to-Sequence Models for Grapheme-to-Phoneme Conversion","display_name":"Multitask Sequence-to-Sequence Models for Grapheme-to-Phoneme Conversion","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2748157908","doi":"https://doi.org/10.21437/interspeech.2017-1436","mag":"2748157908"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1436","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publica.fraunhofer.de/documents/N-476979.html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078278300","display_name":"Benjamin Milde","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Benjamin Milde","raw_affiliation_strings":["Fraunhofer Institute IAIS, Sankt Augustin, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute IAIS, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101519417","display_name":"Christoph Schmidt","orcid":"https://orcid.org/0000-0002-0240-4864"},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Schmidt","raw_affiliation_strings":["Fraunhofer Institute IAIS, Sankt Augustin, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute IAIS, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103573586","display_name":"Joachim K\u00f6hler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joachim K\u00f6hler","raw_affiliation_strings":["Fraunhofer Institute IAIS, Sankt Augustin, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute IAIS, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078278300"],"corresponding_institution_ids":["https://openalex.org/I4210144576"],"apc_list":null,"apc_paid":null,"fwci":3.1203,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93435858,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2536","last_page":"2540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9954000115394592,"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/grapheme","display_name":"Grapheme","score":0.9467269778251648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.816272497177124},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7079505920410156},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6933135986328125},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6079007387161255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5710841417312622},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5448815822601318},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5417921543121338},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5099297761917114},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.4791921377182007},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46308547258377075},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.16815945506095886},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08737453818321228}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.9467269778251648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816272497177124},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7079505920410156},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6933135986328125},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6079007387161255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5710841417312622},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5448815822601318},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5417921543121338},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5099297761917114},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.4791921377182007},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46308547258377075},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.16815945506095886},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08737453818321228},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-1436","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:fraunhofer.de:N-476979","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-476979.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IAIS","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/398963","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/398963","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:fraunhofer.de:N-476979","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-476979.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IAIS","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W118561157","https://openalex.org/W149849615","https://openalex.org/W194249466","https://openalex.org/W1494198834","https://openalex.org/W1506212051","https://openalex.org/W1522301498","https://openalex.org/W1593247906","https://openalex.org/W1902237438","https://openalex.org/W2090755665","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2293770964","https://openalex.org/W2525778437","https://openalex.org/W2550821151","https://openalex.org/W2963299674","https://openalex.org/W2963746123","https://openalex.org/W2963917928","https://openalex.org/W2964050662","https://openalex.org/W2964121744","https://openalex.org/W2964170290","https://openalex.org/W2964199361","https://openalex.org/W2964284687","https://openalex.org/W2964308564","https://openalex.org/W4285719527","https://openalex.org/W4293361313"],"related_works":["https://openalex.org/W2766568248","https://openalex.org/W2463396630","https://openalex.org/W2003136674","https://openalex.org/W3037446006","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361"],"abstract_inverted_index":{"Recently,":[0],"neural":[1],"sequence-to-sequence":[2],"(Seq2Seq)":[3],"models":[4,16,61,135,140],"have":[5],"been":[6],"applied":[7],"to":[8,34,56],"the":[9,23,28,74,117],"problem":[10],"of":[11,21,32,76,116],"grapheme-to-phoneme":[12],"(G2P)":[13],"conversion.":[14,130],"These":[15],"offer":[17],"a":[18],"straightforward":[19],"way":[20],"modeling":[22],"conversion":[24],"by":[25],"jointly":[26],"learning":[27,71,99],"alignment":[29],"and":[30,94,109,126],"translation":[31],"input":[33],"output":[35],"tokens":[36],"in":[37],"an":[38],"end-to-end":[39],"fashion.":[40],"However,":[41],"until":[42],"now":[43],"this":[44,65],"approach":[45],"did":[46],"not":[47,101],"show":[48,102],"improved":[49,103],"error":[50,104,122],"rates":[51],"on":[52,86,124],"its":[53],"own":[54],"compared":[55],"traditional":[57],"joint-sequence":[58],"based":[59,139],"n-gram":[60],"for":[62],"G2P.":[63],"In":[64],"paper,":[66],"we":[67],"investigate":[68],"how":[69],"multitask":[70],"can":[72],"improve":[73],"performance":[75],"Seq2Seq":[77,82,128],"G2P":[78,129,134],"models.":[79],"A":[80],"single":[81],"model":[83,147],"is":[84],"trained":[85],"multiple":[87,92],"phoneme":[88],"lexicon":[89],"datasets":[90,108],"containing":[91],"languages":[93],"phonetic":[95,114],"alphabets.":[96],"Although":[97],"multi-language":[98],"does":[100],"rates,":[105],"combining":[106,132],"standard":[107,137],"crawled":[110],"data":[111],"with":[112,136],"different":[113],"alphabets":[115],"same":[118],"language":[119],"shows":[120],"promising":[121],"reductions":[123],"English":[125],"German":[127],"Finally,":[131],"Seq2seq":[133],"n-grams":[138],"yields":[141],"significant":[142],"improvements":[143],"over":[144],"using":[145],"either":[146],"alone.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}