{"id":"https://openalex.org/W3162508345","doi":"https://doi.org/10.1109/icassp39728.2021.9414292","title":"AISpeech-SJTU Accent Identification System for the Accented English Speech Recognition Challenge","display_name":"AISpeech-SJTU Accent Identification System for the Accented English Speech Recognition Challenge","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162508345","doi":"https://doi.org/10.1109/icassp39728.2021.9414292","mag":"3162508345"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414292","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/A5074673170","display_name":"Houjun Huang","orcid":"https://orcid.org/0000-0003-0757-0949"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houjun Huang","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China","MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055220405","display_name":"Xu Xiang","orcid":"https://orcid.org/0000-0003-2530-9023"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Xiang","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057050425","display_name":"Yexin Yang","orcid":"https://orcid.org/0000-0001-9597-9829"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yexin Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab,Department of Computer Science and Engineering,Shanghai,China","MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063993782","display_name":"Rao Ma","orcid":"https://orcid.org/0000-0002-8552-8992"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rao Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab,Department of Computer Science and Engineering,Shanghai,China","MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab,Department of Computer Science and Engineering,Shanghai,China","MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6254","last_page":"6258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.9979000091552734,"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":0.8063327074050903},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7551901340484619},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7226747870445251},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5704138278961182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48672178387641907},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4674815535545349},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4633190333843231},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4026682674884796},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12772014737129211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063327074050903},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7551901340484619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7226747870445251},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5704138278961182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48672178387641907},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4674815535545349},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4633190333843231},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4026682674884796},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12772014737129211},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414292","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":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W106555234","https://openalex.org/W107354767","https://openalex.org/W1524333225","https://openalex.org/W1686810756","https://openalex.org/W2160564400","https://openalex.org/W2163605009","https://openalex.org/W2187089797","https://openalex.org/W2219249508","https://openalex.org/W2507912506","https://openalex.org/W2515121265","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2946200149","https://openalex.org/W2962780374","https://openalex.org/W2963091184","https://openalex.org/W2963420686","https://openalex.org/W2964243274","https://openalex.org/W2969985801","https://openalex.org/W2970730223","https://openalex.org/W2970971581","https://openalex.org/W2972798094","https://openalex.org/W2973142754","https://openalex.org/W3010925296","https://openalex.org/W3015440759","https://openalex.org/W3024869864","https://openalex.org/W3130041558","https://openalex.org/W3160475509","https://openalex.org/W3163152557","https://openalex.org/W4295312788","https://openalex.org/W6604276704","https://openalex.org/W6604328008","https://openalex.org/W6631362777","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6688816777","https://openalex.org/W6743731764","https://openalex.org/W6763832098","https://openalex.org/W6766978945","https://openalex.org/W6790915370"],"related_works":["https://openalex.org/W1980564716","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W2151922127","https://openalex.org/W4237818736","https://openalex.org/W4367680763","https://openalex.org/W4252005663","https://openalex.org/W2365914832","https://openalex.org/W2352261042","https://openalex.org/W2416299986"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,7,12,33,52,61,86,93,99,110,120,125,140,146],"AISpeech-SJTU":[4],"system":[5,54,111,115,134],"for":[6,39,92],"accent":[8,47,69,89],"identification":[9,48,70],"track":[10],"of":[11,145],"Interspeech-2020":[13],"Accented":[14],"English":[15,26],"Speech":[16],"Recognition":[17],"Challenge.":[18],"In":[19],"this":[20],"challenge":[21,121,141],"track,":[22],"only":[23],"160-hour":[24],"accented":[25],"data":[27,91],"collected":[28],"from":[29],"8":[30],"countries":[31],"and":[32,45,71,103,122],"auxiliary":[34],"Librispeech":[35],"dataset":[36],"are":[37],"provided":[38],"training.":[40],"To":[41],"build":[42],"an":[43],"accurate":[44],"robust":[46],"system,":[49],"we":[50,59,97],"explore":[51],"whole":[53],"pipeline":[55],"in":[56,119,152],"detail.":[57],"First,":[58],"introduce":[60],"ASR":[62],"based":[63,79],"phone":[64],"posteriorgram":[65],"(PPG)":[66],"feature":[67],"to":[68,84,107],"verify":[72],"its":[73],"efficacy.":[74],"Then,":[75],"a":[76,129],"novel":[77],"TTS":[78],"approach":[80],"is":[81,116],"carefully":[82],"designed":[83],"augment":[85],"very":[87],"limited":[88],"training":[90],"first":[94,118],"time.":[95],"Finally,":[96],"propose":[98],"test":[100],"time":[101],"augmentation":[102],"embedding":[104],"fusion":[105],"schemes":[106],"further":[108],"improve":[109],"performance.":[112],"Our":[113],"final":[114],"ranked":[117],"outperforms":[123],"all":[124],"other":[126],"participants":[127],"by":[128,148],"large":[130],"margin.":[131],"The":[132],"submitted":[133],"achieves":[135],"83.63%":[136],"average":[137],"accuracy":[138],"on":[139],"evaluation":[142],"data,":[143],"ahead":[144],"others":[147],"more":[149],"than":[150],"10%":[151],"absolute":[153],"terms.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
