{"id":"https://openalex.org/W3162812479","doi":"https://doi.org/10.1109/icassp39728.2021.9414833","title":"End-To-End Multi-Accent Speech Recognition with Unsupervised Accent Modelling","display_name":"End-To-End Multi-Accent Speech Recognition with Unsupervised Accent Modelling","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162812479","doi":"https://doi.org/10.1109/icassp39728.2021.9414833","mag":"3162812479"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100448180","display_name":"Song Li","orcid":"https://orcid.org/0000-0001-5611-1517"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Li","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Technology,China","School of Electronic Science and Technology, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Technology,China","institution_ids":["https://openalex.org/I75867142"]},{"raw_affiliation_string":"School of Electronic Science and Technology, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066579310","display_name":"Beibei Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beibei Ouyang","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Technology,China","School of Electronic Science and Technology, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Technology,China","institution_ids":["https://openalex.org/I75867142"]},{"raw_affiliation_string":"School of Electronic Science and Technology, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039844745","display_name":"Dexin Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dexin Liao","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054936283","display_name":"Shipeng Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shipeng Xia","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Technology,China","School of Electronic Science and Technology, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Technology,China","institution_ids":["https://openalex.org/I75867142"]},{"raw_affiliation_string":"School of Electronic Science and Technology, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6418","last_page":"6422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9962999820709229,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.993399977684021,"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/computer-science","display_name":"Computer science","score":0.7664833068847656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.762404203414917},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7378901243209839},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6712967753410339},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6227253079414368},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45302221179008484},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.425730437040329},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4196927845478058},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19869354367256165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664833068847656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.762404203414917},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7378901243209839},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6712967753410339},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6227253079414368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45302221179008484},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.425730437040329},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4196927845478058},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19869354367256165},{"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:10.1109/icassp39728.2021.9414833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2402146185","https://openalex.org/W2794490148","https://openalex.org/W2889494795","https://openalex.org/W2890964092","https://openalex.org/W2904459034","https://openalex.org/W2962684181","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962893195","https://openalex.org/W2963272440","https://openalex.org/W2963403868","https://openalex.org/W2964099675","https://openalex.org/W2964243274","https://openalex.org/W2972818416","https://openalex.org/W2973094925","https://openalex.org/W3007328579","https://openalex.org/W3015457435","https://openalex.org/W3044481399","https://openalex.org/W4308252168","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6712930963","https://openalex.org/W6739901393","https://openalex.org/W6750489868"],"related_works":["https://openalex.org/W8738421","https://openalex.org/W2308727","https://openalex.org/W5457946","https://openalex.org/W849475","https://openalex.org/W12667180","https://openalex.org/W12857174","https://openalex.org/W771368","https://openalex.org/W676756","https://openalex.org/W2921871","https://openalex.org/W14754660"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,19,40,63,94],"recognition":[2,6,20,41,64,95],"has":[3],"achieved":[4],"good":[5],"performance":[7,89],"on":[8,99],"standard":[9],"English":[10,25,39,101],"pronunciation":[11],"datasets.":[12],"However,":[13],"one":[14],"prominent":[15],"problem":[16],"with":[17,49,110],"end-to-end":[18,61,92],"systems":[21],"is":[22],"that":[23],"non-native":[24],"speakers":[26],"tend":[27],"to":[28,47,86],"have":[29],"complex":[30],"and":[31,56,83,120,132],"varied":[32],"accents,":[33],"which":[34,75],"reduces":[35],"the":[36,58,88,91,111,129],"accuracy":[37],"of":[38,90,103],"in":[42,128],"different":[43],"countries.":[44],"In":[45,66],"order":[46],"grapple":[48],"such":[50],"an":[51],"issue,":[52],"we":[53,68],"first":[54],"investigate":[55],"improve":[57,87],"current":[59],"mainstream":[60],"multi-accent":[62,93],"technologies.":[65],"addition,":[67],"propose":[69],"two":[70],"unsupervised":[71],"accent":[72,77],"modelling":[73],"methods,":[74],"convert":[76],"information":[78],"into":[79],"a":[80],"global":[81],"embedding,":[82],"use":[84],"it":[85],"systems.":[96],"Experimental":[97],"results":[98],"accented":[100],"datasets":[102],"eight":[104],"countries":[105],"(AESRC2020)":[106],"show":[107],"that,":[108],"compared":[109],"Transformer":[112],"baseline,":[113],"our":[114],"proposed":[115],"methods":[116],"achieve":[117],"relative":[118],"14.8%":[119],"15.4%":[121],"average":[122],"word":[123],"error":[124],"rate":[125],"(WER)":[126],"reduction":[127],"development":[130],"set":[131],"evaluation":[133],"set,":[134],"respectively.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}