{"id":"https://openalex.org/W4214768891","doi":"https://doi.org/10.1109/taslp.2022.3153268","title":"ARoBERT: An ASR Robust Pre-Trained Language Model for Spoken Language Understanding","display_name":"ARoBERT: An ASR Robust Pre-Trained Language Model for Spoken Language Understanding","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4214768891","doi":"https://doi.org/10.1109/taslp.2022.3153268"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3153268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153268","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100373451","display_name":"Chengyu Wang","orcid":"https://orcid.org/0000-0003-1010-9678"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyu Wang","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, Zhejiang, China","Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-1010-9678","affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032461169","display_name":"Suyang Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Suyang Dai","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692711","display_name":"Yipeng Wang","orcid":"https://orcid.org/0000-0003-2092-8888"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yipeng Wang","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065197504","display_name":"Fei Yang","orcid":"https://orcid.org/0000-0003-4802-3191"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yang","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101851065","display_name":"Minghui Qiu","orcid":"https://orcid.org/0000-0002-5184-9886"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghui Qiu","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-5184-9886","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056739524","display_name":"Kehan Chen","orcid":"https://orcid.org/0000-0002-6783-5438"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehan Chen","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103055028","display_name":"Wei Zhou","orcid":"https://orcid.org/0000-0002-7355-6777"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054621636","display_name":"Jun Huang","orcid":"https://orcid.org/0000-0002-7706-7081"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Huang","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9133,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91869026,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"1207","last_page":"1218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.8646721839904785},{"id":"https://openalex.org/keywords/homophone","display_name":"Homophone","score":0.8438528776168823},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.656980037689209},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6232839226722717},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.623125433921814},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6040707230567932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5321432948112488},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5300602316856384},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48375940322875977},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11433917284011841}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8646721839904785},{"id":"https://openalex.org/C160253069","wikidata":"https://www.wikidata.org/wiki/Q221079","display_name":"Homophone","level":2,"score":0.8438528776168823},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.656980037689209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6232839226722717},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.623125433921814},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6040707230567932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321432948112488},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5300602316856384},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48375940322875977},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11433917284011841},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3153268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153268","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G7099683389","display_name":null,"funder_award_id":"LQ21F020004","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W2400002385","https://openalex.org/W2413794162","https://openalex.org/W2618015847","https://openalex.org/W2789348673","https://openalex.org/W2802390314","https://openalex.org/W2889079478","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2899936840","https://openalex.org/W2903250132","https://openalex.org/W2905024391","https://openalex.org/W2962739339","https://openalex.org/W2963288440","https://openalex.org/W2963303028","https://openalex.org/W2963540468","https://openalex.org/W2964110616","https://openalex.org/W2965373594","https://openalex.org/W2972525948","https://openalex.org/W2972991484","https://openalex.org/W2977540023","https://openalex.org/W2980449360","https://openalex.org/W2980689696","https://openalex.org/W2981124540","https://openalex.org/W2981269614","https://openalex.org/W3010452838","https://openalex.org/W3011574394","https://openalex.org/W3015267417","https://openalex.org/W3015469592","https://openalex.org/W3016262400","https://openalex.org/W3034931686","https://openalex.org/W3034999214","https://openalex.org/W3035309733","https://openalex.org/W3045086295","https://openalex.org/W3088409176","https://openalex.org/W3094713728","https://openalex.org/W3096277532","https://openalex.org/W3096926041","https://openalex.org/W3138431698","https://openalex.org/W3196434891","https://openalex.org/W3204887296","https://openalex.org/W3208393080","https://openalex.org/W4206660322","https://openalex.org/W4288089799","https://openalex.org/W6631190155","https://openalex.org/W6687566353","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6766668698","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6802439430"],"related_works":["https://openalex.org/W2358775429","https://openalex.org/W2364211260","https://openalex.org/W1977345729","https://openalex.org/W1567440624","https://openalex.org/W2105439214","https://openalex.org/W2079548008","https://openalex.org/W2030399736","https://openalex.org/W1985374210","https://openalex.org/W4245032792","https://openalex.org/W2371388421"],"abstract_inverted_index":{"Spoken":[0],"Language":[1,130,137],"Understanding":[2],"(SLU)":[3],"aims":[4],"to":[5,14,79,160,172],"interpret":[6],"the":[7,38,91,99,108,145,152,186,197],"meanings":[8],"of":[9,41,83,93,101,107,147,199],"human":[10],"speeches":[11],"in":[12,223],"order":[13],"support":[15],"various":[16],"human-machine":[17],"interaction":[18],"systems.":[19],"A":[20],"key":[21],"technique":[22],"for":[23,125],"SLU":[24,49,84],"is":[25,169],"Automatic":[26],"Speech":[27],"Recognition":[28],"(ASR),":[29],"which":[30,75,155,201],"transcribes":[31],"speech":[32],"signals":[33],"into":[34,151],"text":[35],"contents.":[36],"As":[37],"output":[39],"texts":[40,56,110],"modern":[42],"ASR":[43,59,71,134,175,182],"systems":[44,60],"unavoidably":[45],"contain":[46],"errors,":[47],"mainstream":[48],"models":[50],"either":[51],"trained":[52],"or":[53,115],"tested":[54],"on":[55,214],"transcribed":[57],"by":[58,113],"would":[61],"not":[62],"be":[63,77],"sufficiently":[64],"error":[65],"robust.":[66],"We":[67,206],"present":[68],"ARoBERT,":[69,94,126,200],"an":[70,224],"Robust":[72],"BERT":[73],"model,":[74],"can":[76,180],"fine-tuned":[78],"solve":[80],"a":[81,166,215],"variety":[82],"tasks":[85,124],"with":[86,228],"noisy":[87],"inputs.":[88],"To":[89],"guarantee":[90],"robustness":[92],"during":[95],"pretraining,":[96],"we":[97,118,188],"decrease":[98],"fluctuations":[100],"language":[102],"representations":[103],"when":[104],"some":[105],"parts":[106],"input":[109],"are":[111],"replaced":[112],"homophones":[114,157],"synophones.":[116],"Specifically,":[117],"propose":[119],"two":[120],"novel":[121],"self-supervised":[122],"pre-training":[123,153],"namely":[127],"Phonetically-aware":[128],"Masked":[129,136],"Modeling":[131,138],"(PMLM)":[132],"and":[133,158],"Model-adaptive":[135],"(AMMLM).":[139],"The":[140,194],"PMLM":[141],"task":[142],"explicitly":[143],"fuses":[144],"knowledge":[146],"word":[148],"phonetic":[149],"similarities":[150],"process,":[154],"forces":[156],"synophones":[159],"share":[161],"similar":[162],"representations.":[163],"In":[164,185],"AMMLM,":[165],"data-driven":[167],"algorithm":[168],"further":[170],"introduced":[171],"mine":[173],"typical":[174],"errors":[176],"such":[177],"that":[178,210],"ARoBERT":[179,190,211,219],"tolerate":[181],"model":[183],"errors.":[184],"experiments,":[187],"evaluate":[189],"over":[191],"multiple":[192],"datasets.":[193],"results":[195],"show":[196],"superiority":[198],"consistently":[202],"outperforms":[203,212],"strong":[204],"baselines.":[205],"have":[207],"also":[208],"shown":[209],"state-of-the-arts":[213],"public":[216],"benchmark.":[217],"Currently,":[218],"has":[220],"been":[221],"deployed":[222],"online":[225],"production":[226],"system":[227],"significant":[229],"improvements.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":13}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}