{"id":"https://openalex.org/W3205456388","doi":"https://doi.org/10.21437/interspeech.2022-420","title":"Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge","display_name":"Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3205456388","doi":"https://doi.org/10.21437/interspeech.2022-420","mag":"3205456388"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-420","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-420","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/A5103220846","display_name":"Mutian He","orcid":"https://orcid.org/0000-0002-8939-4207"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Mutian He","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101684375","display_name":"Jingzhou Yang","orcid":"https://orcid.org/0000-0002-5092-6739"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingzhou Yang","raw_affiliation_strings":["Microsoft China"],"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Microsoft China"],"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Frank Soong","raw_affiliation_strings":["Microsoft China"],"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065394791"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.1041,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22135431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"441","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/pronunciation","display_name":"Pronunciation","score":0.8588508367538452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.821174144744873},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8089708089828491},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7813684344291687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5012087821960449},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4761869013309479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45768749713897705},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17680636048316956}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8588508367538452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821174144744873},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8089708089828491},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7813684344291687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5012087821960449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4761869013309479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45768749713897705},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17680636048316956},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-420","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-420","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"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-121395","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-121395","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2551396370","https://openalex.org/W2794592252","https://openalex.org/W2888810455","https://openalex.org/W2889358390","https://openalex.org/W2892280852","https://openalex.org/W2953044594","https://openalex.org/W2962985038","https://openalex.org/W2963792777","https://openalex.org/W2964243274","https://openalex.org/W2970476646","https://openalex.org/W2970568224","https://openalex.org/W2970773744","https://openalex.org/W2972489453","https://openalex.org/W2972585802","https://openalex.org/W2972610613","https://openalex.org/W2972694856","https://openalex.org/W3011874709","https://openalex.org/W3016137096","https://openalex.org/W3035390927","https://openalex.org/W3093388299","https://openalex.org/W3095863137","https://openalex.org/W3113217815","https://openalex.org/W3176023514","https://openalex.org/W3181257032","https://openalex.org/W3185051381","https://openalex.org/W3196568361","https://openalex.org/W3197324626","https://openalex.org/W3197792608","https://openalex.org/W4224932891"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W1831473261","https://openalex.org/W4293870971"],"abstract_inverted_index":{"End-to-end":[0],"TTS":[1,93,127],"requires":[2],"a":[3,26,69,79,102,115,126,169],"large":[4,80],"amount":[5,171],"of":[6,41,172],"speech/text":[7],"paired":[8],"data":[9,43],"to":[10,17,46,54,60,74,85,90,94,104,106,124,165],"cover":[11],"all":[12],"necessary":[13],"knowledge,":[14],"particularly":[15],"how":[16],"pronounce":[18],"different":[19],"words":[20],"in":[21,35,140,153],"diverse":[22],"contexts,":[23],"so":[24],"that":[25,133],"neural":[27,92],"model":[28,128,148],"may":[29],"learn":[30,105],"such":[31,38,95],"knowledge":[32,51,63,109],"accordingly.":[33],"But":[34],"real":[36],"applications,":[37],"high":[39],"demand":[40],"training":[42],"is":[44,122],"hard":[45],"be":[47,55,75,163],"satisfied":[48],"and":[49,158],"additional":[50],"often":[52],"needs":[53,73],"injected":[56],"manually.":[57],"For":[58],"example,":[59],"capture":[61],"pronunciation":[62,82,151],"on":[64,78],"languages":[65,167],"without":[66],"regular":[67],"orthography,":[68],"complicated":[70],"grapheme-to-phoneme":[71],"pipeline":[72],"built":[76],"based":[77],"structured":[81],"lexicon,":[83],"leading":[84],"extra,":[86],"sometimes":[87],"high,":[88],"costs":[89],"extend":[91],"languages.":[96],"In":[97],"this":[98],"paper,":[99],"we":[100],"propose":[101],"framework":[103,121],"automatically":[107],"extract":[108],"from":[110,136],"unstructured":[111],"external":[112],"resources":[113],"using":[114],"novel":[116],"Token2Knowledge":[117],"attention":[118],"module.":[119],"The":[120],"applied":[123],"build":[125],"named":[129],"Neural":[130],"Lexicon":[131],"Reader":[132],"extracts":[134],"pronunciations":[135],"raw":[137],"lexicon":[138],"texts":[139],"an":[141],"end-to-end":[142,155],"manner.":[143],"Experiments":[144],"show":[145],"the":[146,159],"proposed":[147],"significantly":[149],"reduces":[150],"errors":[152],"low-resource,":[154],"Chinese":[156],"TTS,":[157],"lexicon-reading":[160],"capability":[161],"can":[162],"transferred":[164],"other":[166],"with":[168],"smaller":[170],"data.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}