{"id":"https://openalex.org/W3134456927","doi":"https://doi.org/10.21437/interspeech.2021-1888","title":"Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning","display_name":"Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3134456927","doi":"https://doi.org/10.21437/interspeech.2021-1888","mag":"3134456927"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1888","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.05834","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036502813","display_name":"Nilaksh Das","orcid":"https://orcid.org/0000-0002-5281-5549"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nilaksh Das","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050552820","display_name":"Sravan Bodapati","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sravan Bodapati","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014130267","display_name":"Monica Sunkara","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Monica Sunkara","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047128701","display_name":"Sundararajan Srinivasan","orcid":"https://orcid.org/0000-0002-3387-9889"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sundararajan Srinivasan","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020153026","display_name":"Duen Horng Chau","orcid":"https://orcid.org/0000-0001-9824-3323"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Duen Horng Chau","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02481271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1314","last_page":"1318"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9930999875068665,"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":0.9927999973297119,"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":0.7637349367141724},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6780453324317932},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6400101184844971},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6216586828231812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6175759434700012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5261877775192261},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5135005116462708},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4768565595149994},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4605194330215454},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4522474706172943},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43704739212989807},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3907182812690735},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11496996879577637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637349367141724},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6780453324317932},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6400101184844971},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6216586828231812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6175759434700012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5261877775192261},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5135005116462708},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4768565595149994},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4605194330215454},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4522474706172943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43704739212989807},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3907182812690735},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11496996879577637},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1888","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.05834","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.05834","pdf_url":"https://arxiv.org/pdf/2103.05834","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3134456927","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.05834","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.05834","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.05834","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.05834","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.05834","pdf_url":"https://arxiv.org/pdf/2103.05834","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3134456927.pdf","grobid_xml":"https://content.openalex.org/works/W3134456927.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1731081199","https://openalex.org/W2127141656","https://openalex.org/W2510867321","https://openalex.org/W2584667682","https://openalex.org/W2589857635","https://openalex.org/W2593768305","https://openalex.org/W2603679025","https://openalex.org/W2746314669","https://openalex.org/W2889488531","https://openalex.org/W2889494795","https://openalex.org/W2937328535","https://openalex.org/W2945697643","https://openalex.org/W2962684181","https://openalex.org/W2962995362","https://openalex.org/W2972787773","https://openalex.org/W2972889948","https://openalex.org/W2973099347","https://openalex.org/W2973215447","https://openalex.org/W2991213871","https://openalex.org/W3015443711","https://openalex.org/W3015537910","https://openalex.org/W3015974384"],"related_works":["https://openalex.org/W3197285286","https://openalex.org/W2549762342","https://openalex.org/W3015723617","https://openalex.org/W3010079431","https://openalex.org/W1967452917","https://openalex.org/W3124354403","https://openalex.org/W3158284313","https://openalex.org/W2913851961","https://openalex.org/W3082976915","https://openalex.org/W3049079173","https://openalex.org/W3026496355","https://openalex.org/W2599118679","https://openalex.org/W3207222250","https://openalex.org/W3162037819","https://openalex.org/W3016042119","https://openalex.org/W2255778576","https://openalex.org/W3104842308","https://openalex.org/W3148101939","https://openalex.org/W2964161387","https://openalex.org/W3119254916"],"abstract_inverted_index":{"Training":[0],"deep":[1],"neural":[2],"networks":[3],"for":[4,19,23,91],"automatic":[5],"speech":[6,25,59,147],"recognition":[7],"(ASR)":[8],"requires":[9],"large":[10,38,55],"amounts":[11,39,56],"of":[12,40,57,115,145],"transcribed":[13],"speech.":[14],"This":[15],"becomes":[16],"a":[17,99,116,149],"bottleneck":[18],"training":[20,101,130],"robust":[21],"models":[22],"accented":[24,42],"which":[26],"typically":[27],"contains":[28],"high":[29],"variability":[30],"in":[31],"pronunciation":[32],"and":[33,47,107,139],"other":[34],"semantics,":[35],"since":[36],"obtaining":[37],"annotated":[41,133],"data":[43,70],"is":[44],"both":[45],"tedious":[46],"costly.":[48],"Often,":[49],"we":[50,66],"only":[51,83,131],"have":[52],"access":[53],"to":[54,71,75,87],"unannotated":[58,69,146],"from":[60,135,148],"different":[61],"accents.":[62,93],"In":[63],"this":[64,68],"work,":[65],"leverage":[67],"provide":[72],"semantic":[73],"regularization":[74],"an":[76],"ASR":[77,118],"model":[78,119],"that":[79,103],"has":[80],"been":[81],"trained":[82],"on":[84,122,132],"one":[85,136],"accent,":[86,138],"improve":[88],"its":[89],"performance":[90,114],"multiple":[92,128],"We":[94],"propose":[95],"Accent":[96],"Pre-Training":[97],"(Acc-PT),":[98],"semi-supervised":[100],"strategy":[102],"combines":[104],"transfer":[105],"learning":[106],"adversarial":[108],"training.":[109],"Our":[110],"approach":[111],"improves":[112],"the":[113,125],"state-of-the-art":[117],"by":[120],"33%":[121],"average":[123],"over":[124],"baseline":[126],"across":[127],"accents,":[129],"samples":[134],"standard":[137],"as":[140,142],"little":[141],"105":[143],"minutes":[144],"target":[150],"accent.":[151]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}