{"id":"https://openalex.org/W4385823170","doi":"https://doi.org/10.21437/interspeech.2023-2192","title":"Don\u2019t Stop Self-Supervision: Accent Adaptation of Speech Representations via Residual Adapters","display_name":"Don\u2019t Stop Self-Supervision: Accent Adaptation of Speech Representations via Residual Adapters","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823170","doi":"https://doi.org/10.21437/interspeech.2023-2192"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2192","doi":"https://doi.org/10.21437/interspeech.2023-2192","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2192","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.00453","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109774129","display_name":"Anshu Bhatia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anshu Bhatia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049731366","display_name":"Sanchit Sinha","orcid":"https://orcid.org/0000-0003-2650-0612","observed_orcids":["https://orcid.org/0000-0003-2650-0612"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanchit Sinha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027419911","display_name":"Saket Dingliwal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saket Dingliwal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Karthik Gopalakrishnan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karthik Gopalakrishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050552820","display_name":"Sravan Bodapati","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sravan Bodapati","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030","observed_orcids":["https://orcid.org/0000-0002-6645-6030"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0652,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79640305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9833999872207642,"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":0.9833999872207642,"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":0.008299999870359898,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.002099999925121665,"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/accent-adaptation","display_name":"accent adaptation","score":0.8450000286102295},{"id":"https://openalex.org/keywords/speech-representation","display_name":"speech representation","score":0.6980000138282776},{"id":"https://openalex.org/keywords/residual-adapters","display_name":"residual adapters","score":0.9869999885559082},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.7879999876022339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.47200000286102295},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.4699999988079071}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8144018650054932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7085183262825012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6802673935890198},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.596786379814148},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5674879550933838},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44488081336021423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39212724566459656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3384016156196594},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23099225759506226},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-2192","doi":"https://doi.org/10.21437/interspeech.2023-2192","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2192","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2307.00453","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.00453","pdf_url":"https://arxiv.org/pdf/2307.00453","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,"listed_in":[],"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":"doi:10.48550/arxiv.2307.00453","doi":"https://doi.org/10.48550/arxiv.2307.00453","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.00453","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.00453","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.00453","pdf_url":"https://arxiv.org/pdf/2307.00453","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823170.pdf","grobid_xml":"https://content.openalex.org/works/W4385823170.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6902440901","https://openalex.org/W4402111809","https://openalex.org/W2180936379","https://openalex.org/W4372260408","https://openalex.org/W7166464730","https://openalex.org/W7134245636","https://openalex.org/W47152650","https://openalex.org/W4385823404","https://openalex.org/W7204542339","https://openalex.org/W4389519062"],"abstract_inverted_index":{"Speech":[0],"representations":[1,22,58],"learned":[2],"in":[3,62],"a":[4,48,63,103,112],"self-supervised":[5,54],"fashion":[6],"from":[7],"massive":[8],"unlabeled":[9],"speech":[10,57,79],"corpora":[11,32],"have":[12],"been":[13],"adapted":[14],"successfully":[15],"toward":[16,26],"several":[17],"downstream":[18,84,132],"tasks.":[19],"However,":[20],"such":[21,31,60],"may":[23],"be":[24],"skewed":[25],"canonical":[27],"data":[28],"characteristics":[29],"of":[30,56,86,106,115],"and":[33,52,76,111,128,140],"perform":[34],"poorly":[35],"on":[36],"atypical,":[37],"non-native":[38],"accented":[39],"speaker":[40],"populations.":[41],"With":[42],"the":[43,83,118,131],"state-of-the-art":[44],"HuBERT":[45,127],"model":[46,139],"as":[47,82,130],"baseline,":[49],"we":[50],"propose":[51],"investigate":[53],"adaptation":[55],"to":[59],"populations":[61],"parameter-efficient":[64],"way":[65],"via":[66],"training":[67],"accent-specific":[68,109],"residual":[69],"adapters.":[70],"We":[71,88],"experiment":[72],"with":[73,102,108],"4":[74,100],"accents":[75],"choose":[77],"automatic":[78],"recognition":[80],"(ASR)":[81],"task":[85],"interest.":[87],"obtain":[89],"strong":[90],"word":[91],"error":[92],"rate":[93],"reductions":[94],"(WERR)":[95],"over":[96],"HuBERT-large":[97],"for":[98],"all":[99],"accents,":[101],"mean":[104,113],"WERR":[105,114],"22.7%":[107],"adapters":[110],"25.1%":[116],"if":[117],"entire":[119],"encoder":[120],"is":[121,137],"accent-adapted.":[122],"While":[123],"our":[124,134],"experiments":[125],"utilize":[126],"ASR":[129],"task,":[133],"proposed":[135],"approach":[136],"both":[138],"task-agnostic.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2023-08-15T00:00:00"}