{"id":"https://openalex.org/W3016166137","doi":"https://doi.org/10.21437/interspeech.2020-1094","title":"g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset","display_name":"g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3016166137","doi":"https://doi.org/10.21437/interspeech.2020-1094","mag":"3016166137"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1094","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.03136","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073107809","display_name":"Kyubyong Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyubyong Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070831085","display_name":"Seanie Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I58716616","display_name":"Korea Institute of Science and Technology","ror":"https://ror.org/05kzfa883","country_code":"KR","type":"facility","lineage":["https://openalex.org/I27494661","https://openalex.org/I2801339556","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I4387152098","https://openalex.org/I58716616"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seanie Lee","raw_affiliation_strings":["Korea Adv. Inst. of Sci. and Technol"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Adv. Inst. of Sci. and Technol","institution_ids":["https://openalex.org/I58716616","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0833,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82364898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1723","last_page":"1727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9987999796867371,"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":0.9051090478897095},{"id":"https://openalex.org/keywords/pinyin","display_name":"Pinyin","score":0.9037438631057739},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8281556367874146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8027611374855042},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7911187410354614},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7747637033462524},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5249871015548706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5149598717689514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49522772431373596},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.4856196939945221},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4562697112560272},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12634122371673584}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.9051090478897095},{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.9037438631057739},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8281556367874146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027611374855042},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7911187410354614},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7747637033462524},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5249871015548706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149598717689514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49522772431373596},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.4856196939945221},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4562697112560272},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12634122371673584},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1094","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.03136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.03136","pdf_url":"https://arxiv.org/pdf/2004.03136","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3016166137","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.03136.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.03136","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.03136","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.03136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.03136","pdf_url":"https://arxiv.org/pdf/2004.03136","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3016166137.pdf","grobid_xml":"https://content.openalex.org/works/W3016166137.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1973424788","https://openalex.org/W2064675550","https://openalex.org/W2080069570","https://openalex.org/W2126849693","https://openalex.org/W2147880316","https://openalex.org/W2150622925","https://openalex.org/W2158912874","https://openalex.org/W2612199078","https://openalex.org/W2792643794","https://openalex.org/W2972457126","https://openalex.org/W2972903407","https://openalex.org/W3011874709","https://openalex.org/W3103145119","https://openalex.org/W3210120707"],"related_works":["https://openalex.org/W3095762785","https://openalex.org/W3192338856","https://openalex.org/W2743923735","https://openalex.org/W2405860391","https://openalex.org/W2946445149","https://openalex.org/W2786638153","https://openalex.org/W3049269430","https://openalex.org/W3037446006","https://openalex.org/W2113528982","https://openalex.org/W2887191217","https://openalex.org/W3160200750","https://openalex.org/W3015291419","https://openalex.org/W80018330","https://openalex.org/W2401271578","https://openalex.org/W3037190132","https://openalex.org/W2091116114","https://openalex.org/W3089901025","https://openalex.org/W2894993184","https://openalex.org/W2979286696","https://openalex.org/W2509805446"],"abstract_inverted_index":{"Conversion":[0],"of":[1,18,32,70,107],"Chinese":[2,13,23,86,111],"graphemes":[3],"to":[4,28,46,65,76,84],"phonemes":[5],"(G2P)":[6],"is":[7,26],"an":[8],"essential":[9],"component":[10],"in":[11,22,96],"Mandarin":[12],"Text-To-Speech":[14],"(TTS)":[15],"systems.":[16,131],"One":[17],"the":[19,30,71],"biggest":[20],"challenges":[21],"G2P":[24,130],"conversion":[25],"how":[27],"disambiguate":[29],"pronunciation":[31],"polyphones":[33],"-":[34],"characters":[35],"having":[36],"multiple":[37],"pronunciations.":[38],"Although":[39],"many":[40],"academic":[41],"efforts":[42],"have":[43],"been":[44,51],"made":[45],"address":[47],"it,":[48,122],"there":[49],"has":[50],"no":[52],"open":[53],"dataset":[54,104],"that":[55,105,125],"can":[56],"serve":[57],"as":[58],"a":[59,101,116],"standard":[60],"benchmark":[61,103],"for":[62,78,110],"fair":[63],"comparison":[64],"date.":[66],"In":[67],"addition,":[68],"most":[69],"reported":[72],"systems":[73],"are":[74],"hard":[75],"employ":[77],"researchers":[79],"or":[80],"practitioners":[81],"who":[82],"want":[83],"convert":[85],"text":[87],"into":[88],"pinyin":[89],"at":[90],"their":[91],"convenience.":[92],"Motivated":[93],"by":[94],"these,":[95],"this":[97],"work,":[98],"we":[99,133],"introduce":[100],"new":[102],"consists":[106],"99,000+":[108],"sentences":[109],"polyphone":[112],"disambiguation.":[113],"We":[114],"train":[115],"simple":[117],"neural":[118],"network":[119],"model":[120],"on":[121,140],"and":[123,137],"find":[124],"it":[126,139],"outperforms":[127],"other":[128],"preexisting":[129],"Finally,":[132],"package":[134],"our":[135],"project":[136],"share":[138],"PyPi.":[141]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}