{"id":"https://openalex.org/W2965116050","doi":"https://doi.org/10.1109/taslp.2019.2933146","title":"Adversarial Regularization for Attention Based End-to-End Robust Speech Recognition","display_name":"Adversarial Regularization for Attention Based End-to-End Robust Speech Recognition","publication_year":2019,"publication_date":"2019-08-05","ids":{"openalex":"https://openalex.org/W2965116050","doi":"https://doi.org/10.1109/taslp.2019.2933146","mag":"2965116050"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2933146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2933146","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/A5102880200","display_name":"Sining Sun","orcid":"https://orcid.org/0000-0002-2642-5096"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sining Sun","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-2642-5096","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8234-0823","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112467501","display_name":"Mei-Yuh Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei-Yuh Hwang","raw_affiliation_strings":["Mobvoi AI Lab, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobvoi AI Lab, Redmond, WA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1062,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93368816,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"27","issue":"11","first_page":"1826","last_page":"1838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11309","display_name":"Music and Audio Processing","score":0.989799976348877,"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/T10860","display_name":"Speech and Audio Processing","score":0.9860000014305115,"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":0.713430643081665},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6592594981193542},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6519601345062256},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5731217861175537},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5680400133132935},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5312076807022095},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5213016867637634},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5197427272796631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4343036115169525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33892786502838135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713430643081665},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6592594981193542},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6519601345062256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5731217861175537},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5680400133132935},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5312076807022095},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5213016867637634},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5197427272796631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4343036115169525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33892786502838135},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2933146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2933146","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":[],"awards":[{"id":"https://openalex.org/G7845190039","display_name":null,"funder_award_id":"61571363","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":80,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W769612788","https://openalex.org/W1663973292","https://openalex.org/W1731081199","https://openalex.org/W1828163288","https://openalex.org/W1882958252","https://openalex.org/W1902237438","https://openalex.org/W1945616565","https://openalex.org/W1989549063","https://openalex.org/W2099471712","https://openalex.org/W2122860281","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2157331557","https://openalex.org/W2219249508","https://openalex.org/W2327501763","https://openalex.org/W2510867321","https://openalex.org/W2526425061","https://openalex.org/W2584667682","https://openalex.org/W2587088898","https://openalex.org/W2735006420","https://openalex.org/W2766219058","https://openalex.org/W2770312844","https://openalex.org/W2782403400","https://openalex.org/W2795050058","https://openalex.org/W2795867901","https://openalex.org/W2796339975","https://openalex.org/W2801581493","https://openalex.org/W2889048668","https://openalex.org/W2889163603","https://openalex.org/W2889213362","https://openalex.org/W2891933988","https://openalex.org/W2898435086","https://openalex.org/W2907262790","https://openalex.org/W2916997151","https://openalex.org/W2936774411","https://openalex.org/W2938873567","https://openalex.org/W2942203175","https://openalex.org/W2962684181","https://openalex.org/W2962718684","https://openalex.org/W2962778134","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962893195","https://openalex.org/W2962995362","https://openalex.org/W2963207607","https://openalex.org/W2963211739","https://openalex.org/W2963242190","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963542245","https://openalex.org/W2963747784","https://openalex.org/W2963821905","https://openalex.org/W2963826681","https://openalex.org/W2963917611","https://openalex.org/W2963929654","https://openalex.org/W2963970535","https://openalex.org/W2964040467","https://openalex.org/W2964159205","https://openalex.org/W2964301649","https://openalex.org/W4212863985","https://openalex.org/W4236060934","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6622262455","https://openalex.org/W6629510986","https://openalex.org/W6637618735","https://openalex.org/W6638749077","https://openalex.org/W6639480849","https://openalex.org/W6640425456","https://openalex.org/W6688816777","https://openalex.org/W6732862412","https://openalex.org/W6739901393","https://openalex.org/W6746295503","https://openalex.org/W6746882984","https://openalex.org/W6754473786","https://openalex.org/W6755779437","https://openalex.org/W6761827036"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W2145230572","https://openalex.org/W2166312020","https://openalex.org/W4401751953","https://openalex.org/W2914064142","https://openalex.org/W156567445","https://openalex.org/W3136989387","https://openalex.org/W4287266619","https://openalex.org/W3082335021"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,25,230],"recognition,":[2],"such":[3,45],"as":[4,46],"attention":[5,79],"based":[6,80],"approaches,":[7],"is":[8,69,134,220],"an":[9,135],"emerging":[10],"and":[11,33,107,128,179,201],"attractive":[12],"topic":[13],"in":[14,41,61,74],"recent":[15],"years.":[16],"It":[17],"has":[18],"achieved":[19,210],"comparable":[20],"performance":[21],"with":[22,94],"the":[23,39,42,54,78,91,103,108,158,165,175,191,196,204,221],"traditional":[24],"recognition":[26,231],"framework.":[27],"Because":[28],"end-to-end":[29,67,81],"approaches":[30],"integrate":[31],"acoustic":[32,43,47],"linguistic":[34,55],"information":[35],"into":[36],"one":[37],"model,":[38],"perturbation":[40],"level":[44],"noise,":[48],"could":[49],"be":[50],"easily":[51],"propagated":[52],"to":[53,76,115,138,228],"level.":[56],"Thus":[57],"improving":[58],"model":[59,82],"robustness":[60,140],"real":[62],"application":[63,224],"environments":[64],"for":[65,143],"these":[66],"systems":[68],"crucial.":[70],"In":[71],"this":[72,219],"paper,":[73],"order":[75],"make":[77],"more":[83,181],"robust":[84],"against":[85,141],"noises,":[86],"we":[87,148,169,209],"formulate":[88],"regulation":[89],"of":[90,225],"objective":[92],"function":[93],"adversarial":[95,100,132,226],"training":[96,176,199],"examples.":[97],"Particularly":[98],"two":[99,121],"regularization":[101,133,227],"techniques,":[102],"fast":[104],"gradient-sign":[105],"method":[106],"local":[109],"distributional":[110],"smoothness":[111],"method,":[112],"are":[113],"explored":[114],"improve":[116,139],"noise":[117],"robustness.":[118],"Experiments":[119],"on":[120,157,164,195,203],"publicly":[122],"available":[123],"Chinese":[124],"Mandarin":[125],"corpora,":[126],"AISHELL-1":[127,159],"AISHELL-2,":[129],"show":[130],"that":[131,190],"effective":[136,188],"approach":[137],"noises":[142],"our":[144,184,217],"attention-based":[145],"models.":[146],"Specifically,":[147],"obtained":[149],"18.4%":[150],"relative":[151,172,212],"character":[152],"error":[153,213],"rate":[154,214],"(CER)":[155],"reduction":[156],"noisy":[160],"test":[161,167,207],"set.":[162],"Even":[163],"clean":[166],"set,":[168],"showed":[170],"16.7%":[171],"improvement.":[173],"As":[174],"set":[177],"increases":[178],"covers":[180],"environmental":[182],"varieties,":[183],"proposed":[185],"methods":[186],"remain":[187],"despite":[189],"improvement":[192],"shrinks.":[193],"Training":[194],"large":[197],"AISHELL-2":[198,206],"corpus":[200],"testing":[202],"various":[205],"sets,":[208],"7.0%-12.2%":[211],"reduction.":[215],"To":[216],"knowledge,":[218],"first":[222],"successful":[223],"sequence-to-sequence":[229],"systems.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}