{"id":"https://openalex.org/W3163152557","doi":"https://doi.org/10.1109/icassp39728.2021.9414471","title":"AISpeech-SJTU ASR System for the Accented English Speech Recognition Challenge","display_name":"AISpeech-SJTU ASR System for the Accented English Speech Recognition Challenge","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163152557","doi":"https://doi.org/10.1109/icassp39728.2021.9414471","mag":"3163152557"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414471","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":"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/A5101667381","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0002-4723-0044"},"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":true,"raw_author_name":"Tian Tan","raw_affiliation_strings":["AISpeech Ltd, Suzhou, China","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070663","display_name":"Yizhou Lu","orcid":"https://orcid.org/0000-0003-1399-8079"},"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":"Yizhou Lu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, 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":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100554020","display_name":"Sen Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sen Zhu","raw_affiliation_strings":["AISpeech Ltd, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102913261","display_name":"Jiaqi Guo","orcid":"https://orcid.org/0009-0005-4168-5098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqi Guo","raw_affiliation_strings":["AISpeech Ltd, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"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":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101667381"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.236,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89830676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6413","last_page":"6417"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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":0.9941999912261963,"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/speech-recognition","display_name":"Speech recognition","score":0.7989683151245117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.785333514213562},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6894969344139099},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5490512847900391},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5410169363021851},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49279382824897766},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4877689480781555},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4242076873779297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41432827711105347},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39149796962738037},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08276623487472534}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7989683151245117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.785333514213562},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6894969344139099},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5490512847900391},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5410169363021851},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49279382824897766},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4877689480781555},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4242076873779297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41432827711105347},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39149796962738037},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08276623487472534},{"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/icassp39728.2021.9414471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414471","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":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1537735731","https://openalex.org/W1978660892","https://openalex.org/W2062164080","https://openalex.org/W2106440210","https://openalex.org/W2130414229","https://openalex.org/W2327501763","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2587080466","https://openalex.org/W2603679025","https://openalex.org/W2696967604","https://openalex.org/W2787726985","https://openalex.org/W2891756742","https://openalex.org/W2916979304","https://openalex.org/W2936774411","https://openalex.org/W2938374794","https://openalex.org/W2946200149","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962893195","https://openalex.org/W2963091184","https://openalex.org/W2963250244","https://openalex.org/W2963266252","https://openalex.org/W2963403868","https://openalex.org/W2964002616","https://openalex.org/W2964309797","https://openalex.org/W2970730223","https://openalex.org/W2972815379","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3008762051","https://openalex.org/W3130041558","https://openalex.org/W3133187441","https://openalex.org/W3160475509","https://openalex.org/W3162508345","https://openalex.org/W4299655595","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6631959037","https://openalex.org/W6638575559","https://openalex.org/W6739901393","https://openalex.org/W6763832098","https://openalex.org/W6790915370","https://openalex.org/W6791105188"],"related_works":["https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2145230572","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2146197305","https://openalex.org/W2166312020","https://openalex.org/W2033669961","https://openalex.org/W2134950286"],"abstract_inverted_index":{"This":[0,16],"paper":[1],"describes":[2],"the":[3,8,22,44,51,56,93,108,114,121,147],"AISpeech-SJTU":[4],"ASR":[5],"system":[6,78,112],"for":[7],"Interspeech-2020":[9],"Accented":[10],"English":[11],"Speech":[12],"Recognition":[13],"Challenge":[14],"(AESRC).":[15],"task":[17],"is":[18],"challenging":[19],"due":[20],"to":[21,38,86],"diversity":[23],"of":[24,31,130,146],"pronunciation":[25,30],"accuracy,":[26],"intonation":[27],"speed":[28,68],"and":[29,46,70,81,107,135,151],"some":[32],"syllables.":[33],"All":[34],"participants":[35],"were":[36,101],"restricted":[37],"develop":[39],"their":[40],"systems":[41,154],"based":[42],"on":[43,132,138,143],"speech":[45],"text":[47],"corpora":[48],"provided":[49],"by":[50,103],"organizer.":[52],"To":[53],"work":[54],"around":[55],"data-scarcity":[57],"problem,":[58],"data":[59],"augmentation":[60],"was":[61,79,84],"first":[62],"explored":[63],"including":[64],"noise":[65],"simulation,":[66],"SpecAugment,":[67],"perturbation":[69],"TTS":[71],"simulation.":[72],"Moreover,":[73],"SOTA":[74],"CNN-transformer-based":[75],"joint":[76],"CTC-attention":[77],"built":[80],"accent":[82,89],"adaptation":[83],"proposed":[85],"train":[87],"an":[88],"robust":[90],"system.":[91],"Finally,":[92],"first-pass":[94],"recognition":[95],"hypotheses":[96],"generated":[97],"from":[98],"CTC":[99],"head":[100],"rescored":[102],"forward,":[104],"backward":[105],"LSTM-LM":[106],"attention":[109],"head.":[110],"Our":[111],"with":[113],"best":[115],"configuration":[116],"achieves":[117],"second":[118,149],"place":[119],"in":[120,124],"challenge,":[122],"resulting":[123],"a":[125],"word":[126],"error":[127],"rate":[128],"(WER)":[129],"4.00%":[131],"dev":[133],"set":[134,145],"4.47%":[136],"WER":[137,142],"test":[139,144],"set,":[140],"while":[141],"top-performing,":[148],"runner-up":[150],"official":[152],"baseline":[153],"are":[155],"4.06%,":[156],"4.52%,":[157],"8.29%,":[158],"respectively.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}