{"id":"https://openalex.org/W4296068794","doi":"https://doi.org/10.21437/interspeech.2022-836","title":"Mitigating bias against non-native accents","display_name":"Mitigating bias against non-native accents","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068794","doi":"https://doi.org/10.21437/interspeech.2022-836"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-836","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-836","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_d76bd44c-6057-4c2d-a23c-8939505953a1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100320673","display_name":"Yuanyuan Zhang","orcid":"https://orcid.org/0000-0002-9078-9062"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhang","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103286521","display_name":"Yixuan Zhang","orcid":"https://orcid.org/0009-0007-8637-3199"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yixuan Zhang","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064554048","display_name":"Bence Halpern","orcid":null},"institutions":[{"id":"https://openalex.org/I2898336195","display_name":"The Netherlands Cancer Institute","ror":"https://ror.org/03xqtf034","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I2898336195"]},{"id":"https://openalex.org/I4210111138","display_name":"Oncode Institute","ror":"https://ror.org/01n92vv28","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210111138"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bence Halpern","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands","Netherlands Cancer Institute, Amsterdam, the Netherlands","ACLC, University of Amsterdam, Amsterdam, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Netherlands Cancer Institute, Amsterdam, the Netherlands","institution_ids":["https://openalex.org/I2898336195","https://openalex.org/I4210111138"]},{"raw_affiliation_string":"ACLC, University of Amsterdam, Amsterdam, the Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071210435","display_name":"Tanvina Patel","orcid":"https://orcid.org/0000-0002-9544-0038"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tanvina Patel","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3168","last_page":"3172"},"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":0.9944999814033508,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7208578586578369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7172109484672546},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6234129071235657},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6111331582069397},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5037855505943298},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.4633062481880188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3655407428741455},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3319321870803833}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7208578586578369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7172109484672546},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6234129071235657},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6111331582069397},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5037855505943298},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.4633062481880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3655407428741455},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3319321870803833},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-836","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-836","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:3968d19a-1ae4-41d4-9491-e088c389da24","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:3968d19a-1ae4-41d4-9491-e088c389da24","pdf_url":"https://repository.tudelft.nl/file/File_d76bd44c-6057-4c2d-a23c-8939505953a1","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},{"id":"pmh:oai:tudelft.nl:uuid:bc989a6e-60b5-4cff-bb7f-999c616afc7c","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:bc989a6e-60b5-4cff-bb7f-999c616afc7c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:3968d19a-1ae4-41d4-9491-e088c389da24","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:3968d19a-1ae4-41d4-9491-e088c389da24","pdf_url":"https://repository.tudelft.nl/file/File_d76bd44c-6057-4c2d-a23c-8939505953a1","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296068794.pdf","grobid_xml":"https://content.openalex.org/works/W4296068794.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W29952999","https://openalex.org/W1556869580","https://openalex.org/W2407080277","https://openalex.org/W2696967604","https://openalex.org/W2936774411","https://openalex.org/W2962684181","https://openalex.org/W2962788625","https://openalex.org/W2973094925","https://openalex.org/W2998572311","https://openalex.org/W3012624518","https://openalex.org/W3015723617","https://openalex.org/W3026041220","https://openalex.org/W3036601975","https://openalex.org/W3093579165","https://openalex.org/W3096338464","https://openalex.org/W3097017391","https://openalex.org/W3097777922","https://openalex.org/W3139918052","https://openalex.org/W3147107444","https://openalex.org/W3160525311","https://openalex.org/W3162061711","https://openalex.org/W3163475957","https://openalex.org/W3167533889","https://openalex.org/W3181410678","https://openalex.org/W3197285286","https://openalex.org/W3201401182","https://openalex.org/W3210685431","https://openalex.org/W4226033575"],"related_works":["https://openalex.org/W4256576465","https://openalex.org/W2119316621","https://openalex.org/W2348537528","https://openalex.org/W2532006889","https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2547793174","https://openalex.org/W2132658536","https://openalex.org/W2070212102"],"abstract_inverted_index":{"<p>Automatic":[0],"speech":[1,41,99,133],"recognition":[2],"(ASR)":[3],"systems":[4],"have":[5],"seen":[6],"substantial":[7],"improvements":[8],"in":[9,33,102],"the":[10,53,94,129,151,157,171,178,188,195],"past":[11],"decade;":[12],"however,":[13],"not":[14],"for":[15,45,156],"all":[16],"speaker":[17],"groups.":[18],"Recent":[19],"research":[20],"shows":[21],"that":[22,145],"bias":[23,57,65,152,180,189],"exists":[24],"against":[25,67,153,181,190],"different":[26,72],"types":[27],"of":[28,48,96,197],"speech,":[29],"including":[30],"non-native":[31,68,97,131,154,191],"accents,":[32],"state-of-the-art":[34],"(SOTA)":[35],"ASR":[36,44,162],"systems.":[37],"To":[38],"attain":[39],"inclusive":[40],"recognition,":[42],"i.e.,":[43,116],"everyone":[46],"irrespective":[47],"how":[49],"one":[50,55],"speaks":[51],"or":[52],"accent":[54],"has,":[56],"mitigation":[58,66],"is":[59],"necessary.":[60],"Here":[61],"we":[62,111],"focus":[63],"on":[64],"accents":[69,155,192],"using":[70,78],"two":[71,113],"approaches:":[73],"data":[74,101,105,134,147,169],"augmentation":[75,106,148],"and":[76,118,166,177,185],"by":[77],"more":[79,135],"effective":[80],"training":[81,100,114,121,140],"methods.":[82],"We":[83],"used":[84],"an":[85],"autoencoder-based":[86],"cross-lingual":[87],"voice":[88],"conversion":[89],"(VC)":[90],"model":[91],"to":[92,104,123],"increase":[93],"amount":[95],"accented":[98,132],"addition":[103],"through":[107],"speed":[108,167],"perturbation.":[109],"Moreover,":[110],"investigate":[112],"methods,":[115],"fine-tuning":[117],"domain":[119],"adversarial":[120],"(DAT),":[122],"see":[124],"whether":[125],"they":[126],"can":[127],"use":[128],"limited":[130],"effectively":[136],"than":[137],"a":[138],"standard":[139],"approach.":[141],"Experimental":[142],"results":[143],"show":[144],"VC-based":[146],"successfully":[149],"mitigates":[150],"SOTA":[158],"end-to-end":[159],"(E2E)":[160],"Dutch":[161],"system.":[163],"Combining":[164],"VC":[165],"perturbed":[168],"gave":[170],"lowest":[172],"word":[173],"error":[174],"rate":[175],"(WER)":[176],"smallest":[179],"nonnative":[182],"accents.":[183],"Fine-tuning":[184],"DAT":[186],"reduced":[187],"but":[193],"at":[194],"cost":[196],"native":[198],"performance.</p>":[199]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}