{"id":"https://openalex.org/W4296068433","doi":"https://doi.org/10.21437/interspeech.2022-229","title":"A polyphone BERT for Polyphone Disambiguation in Mandarin Chinese","display_name":"A polyphone BERT for Polyphone Disambiguation in Mandarin Chinese","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068433","doi":"https://doi.org/10.21437/interspeech.2022-229"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-229","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-229","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5100366539","display_name":"Song Zhang","orcid":"https://orcid.org/0000-0002-4893-9565"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Song Zhang","raw_affiliation_strings":["SenseTime Research"],"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109480444","display_name":"Ken Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ken Zheng","raw_affiliation_strings":["SenseTime Research"],"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100520298","display_name":"Xiaoxu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxu Zhu","raw_affiliation_strings":["SenseTime Research"],"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003607066","display_name":"Baoxiang Li","orcid":"https://orcid.org/0009-0009-4490-2157"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baoxiang Li","raw_affiliation_strings":["SenseTime Research"],"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100366539"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5197,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63353803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8499683737754822},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7426058650016785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5303913950920105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42767634987831116},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33302685618400574},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2342420518398285}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8499683737754822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426058650016785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5303913950920105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42767634987831116},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33302685618400574},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2342420518398285},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-229","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-229","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1593247906","https://openalex.org/W1940872118","https://openalex.org/W1999965501","https://openalex.org/W2024632416","https://openalex.org/W2355260830","https://openalex.org/W2612199078","https://openalex.org/W2804552794","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W2972457126","https://openalex.org/W2972585802","https://openalex.org/W2972881244","https://openalex.org/W3095863137","https://openalex.org/W4287547221","https://openalex.org/W4297801719"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2374317326","https://openalex.org/W2990005675","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Grapheme-to-phoneme":[0],"(G2P)":[1],"conversion":[2,19],"is":[3,20,29,104,162],"an":[4],"indispensable":[5],"part":[6],"of":[7,17,25,57,109,127,136,152],"the":[8,15,23,33,55,107,119,128,134,137,141,157,163],"Chinese":[9,41,49,58,65,71,79,86,91,111,129],"Mandarin":[10],"text-to-speech":[11],"(TTS)":[12],"system,":[13],"and":[14,94,140],"core":[16],"G2P":[18],"to":[21,30,53,149],"solve":[22],"problem":[24],"polyphone":[26,50,80,120,130,142,167],"disambiguation,":[27],"which":[28,103,161],"pick":[31],"up":[32],"correct":[34],"pronunciation":[35],"for":[36,39,100],"several":[37],"candidates":[38],"a":[40,48,78,84,96,124],"polyphonic":[42,59,72,112],"character.In":[43],"this":[44,114],"paper,":[45],"we":[46,61,76,116],"propose":[47],"BERT":[51,81,87,143],"model":[52,144],"predict":[54],"pronunciations":[56],"characters.Firstly,":[60],"create":[62],"741":[63,89],"new":[64,90,101],"monophonic":[66,92],"characters":[67,73,93],"from":[68],"354":[69],"source":[70,110],"by":[74,82,106],"pronunciation.Then":[75],"get":[77],"extending":[83],"pre-trained":[85],"with":[88,156],"adding":[95],"corresponding":[97],"embedding":[98],"layer":[99],"tokens,":[102],"initialized":[105],"embeddings":[108],"characters.In":[113],"way,":[115],"can":[117],"turn":[118],"disambiguation":[121],"task":[122,126],"into":[123],"pre-training":[125],"BERT.Experimental":[131],"results":[132],"demonstrate":[133],"effectiveness":[135],"proposed":[138],"model,":[139,160],"obtain":[145],"2%":[146],"(from":[147],"92.1%":[148],"94.1%)":[150],"improvement":[151],"average":[153],"accuracy":[154],"compared":[155],"BERT-based":[158],"classifier":[159],"prior":[164],"state-of-the-art":[165],"in":[166],"disambiguation.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}