{"id":"https://openalex.org/W4372346106","doi":"https://doi.org/10.1109/icassp49357.2023.10094891","title":"G2PL: Lexicon Enhanced Chinese Polyphone Disambiguation Using Bert Adapter with a New Dataset","display_name":"G2PL: Lexicon Enhanced Chinese Polyphone Disambiguation Using Bert Adapter with a New Dataset","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346106","doi":"https://doi.org/10.1109/icassp49357.2023.10094891"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"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/A5017508119","display_name":"Haifeng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Zhao","raw_affiliation_strings":["Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076724246","display_name":"Hongzhi Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Wan","raw_affiliation_strings":["Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729418","display_name":"Lili Huang","orcid":"https://orcid.org/0000-0002-8753-3170"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lili Huang","raw_affiliation_strings":["Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071321197","display_name":"Mingwei Cao","orcid":"https://orcid.org/0000-0002-8161-0382"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingwei Cao","raw_affiliation_strings":["Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04201036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.883220374584198},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6709911227226257},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.6698494553565979},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.6658356785774231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6126383543014526},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5403033494949341},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.535888135433197},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5148800611495972},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45589613914489746},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3900267481803894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.883220374584198},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6709911227226257},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.6698494553565979},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.6658356785774231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126383543014526},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5403033494949341},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.535888135433197},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5148800611495972},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45589613914489746},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3900267481803894},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-135446","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1520-6149&rft.volume=&rft.issue=&rft.date=2023&rft.spage=&rft.aulast=Zhao&rft.aufirst=Haifeng&rft.atitle=G2PL%3A+Lexicon+Enhanced+Chinese+Polyphone+Disambiguation+Using+Bert+Adapter+with+a+New+Dataset&rft.title=ICASSP%2C+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+-+Proceedings","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2126849693","https://openalex.org/W2147880316","https://openalex.org/W2158912874","https://openalex.org/W2612199078","https://openalex.org/W2804552794","https://openalex.org/W2896457183","https://openalex.org/W2972585802","https://openalex.org/W3095762785","https://openalex.org/W3095863137","https://openalex.org/W3176023514","https://openalex.org/W3196649516","https://openalex.org/W4296068408","https://openalex.org/W6631190155","https://openalex.org/W6682082992","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W2133028525","https://openalex.org/W4385352507","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W4391124013","https://openalex.org/W2080578089","https://openalex.org/W2179005426","https://openalex.org/W2949933325","https://openalex.org/W4289749661"],"abstract_inverted_index":{"Polyphone":[0],"disambiguation":[1],"is":[2,16,45],"the":[3,9,31,37,75,82,90,96,100],"core":[4],"of":[5,19,35,39,84,93],"grapheme-to-phoneme(G2P)":[6],"module":[7],"for":[8,25,42,69],"Chinese":[10],"speech":[11],"synthesis":[12],"system.":[13],"However,":[14],"there":[15],"a":[17,56,66],"lack":[18],"datasets":[20],"and":[21,109,115],"only":[22],"one":[23],"public":[24,110],"polyphone":[26],"disambiguation.":[27],"Moreover,":[28],"due":[29],"to":[30,86,103],"double":[32],"long-tail":[33],"distribution":[34],"polyphones,":[36],"ratio":[38],"pronunciation":[40,92],"data":[41],"most":[43],"polyphones":[44],"extremely":[46],"unbalanced":[47],"after":[48],"sampling.":[49,70],"To":[50],"solve":[51],"these":[52],"problems,":[53],"we":[54,73,98],"propose":[55,74],"new":[57,67],"dataset":[58],"with":[59],"57,000":[60],"sentences":[61],"from":[62],"various":[63],"domains":[64],"by":[65],"strategy":[68],"In":[71,95],"addition,":[72],"G2PL,":[76],"which":[77],"integrates":[78],"word":[79],"features":[80],"into":[81],"bottom":[83],"BERT":[85],"assist":[87],"in":[88],"predicting":[89],"correct":[91],"polyphone.":[94],"experiment,":[97],"train":[99],"G2PL":[101],"model":[102],"outperform":[104],"other":[105],"methods":[106],"on":[107],"our":[108],"datasets.":[111],"Our":[112],"dataset,":[113],"codes":[114],"user-friendly":[116],"package":[117],"are":[118],"freely":[119],"available.":[120]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
