{"id":"https://openalex.org/W4210403363","doi":"https://doi.org/10.1109/asru51503.2021.9688063","title":"Leveraging Linguistic Knowledge for Accent Robustness of End-to-End Models","display_name":"Leveraging Linguistic Knowledge for Accent Robustness of End-to-End Models","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210403363","doi":"https://doi.org/10.1109/asru51503.2021.9688063"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688063","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/8c0bf78e-f32f-4b6b-89b0-c0aec7c74ae7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066016980","display_name":"Andrea Carmantini","orcid":"https://orcid.org/0000-0001-9016-5092"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Andrea Carmantini","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh,Edinburgh,UK,EH8 9AB"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh,Edinburgh,UK,EH8 9AB","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh,Edinburgh,UK,EH8 9AB"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh,Edinburgh,UK,EH8 9AB","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh,Edinburgh,UK,EH8 9AB"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh,Edinburgh,UK,EH8 9AB","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066016980"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21564778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"803","last_page":"810"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9977999925613403,"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":0.7548151016235352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6043717861175537},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5937974452972412},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5905933380126953},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4668933153152466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4364805817604065},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.413248211145401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548151016235352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6043717861175537},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5937974452972412},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5905933380126953},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4668933153152466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4364805817604065},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.413248211145401},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru51503.2021.9688063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688063","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/8c0bf78e-f32f-4b6b-89b0-c0aec7c74ae7","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/8c0bf78e-f32f-4b6b-89b0-c0aec7c74ae7","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Carmantini, A, Renals, S & Bell, P 2022, Leveraging Linguistic Knowledge for Accent Robustness of End-to-End Models. in Proceedings of the 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers, pp. 803-810, IEEE Automatic Speech Recognition and Understanding Workshop 2021, Cartagena, Colombia, 13/12/21. https://doi.org/10.1109/ASRU51503.2021.9688063","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/8c0bf78e-f32f-4b6b-89b0-c0aec7c74ae7","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/9688063","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/8c0bf78e-f32f-4b6b-89b0-c0aec7c74ae7","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/8c0bf78e-f32f-4b6b-89b0-c0aec7c74ae7","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Carmantini, A, Renals, S & Bell, P 2022, Leveraging Linguistic Knowledge for Accent Robustness of End-to-End Models. in Proceedings of the 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers, pp. 803-810, IEEE Automatic Speech Recognition and Understanding Workshop 2021, Cartagena, Colombia, 13/12/21. https://doi.org/10.1109/ASRU51503.2021.9688063","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1999185623","https://openalex.org/W2024490156","https://openalex.org/W2149353989","https://openalex.org/W2295754094","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2587080466","https://openalex.org/W2603679025","https://openalex.org/W2756127416","https://openalex.org/W2889494795","https://openalex.org/W2890197052","https://openalex.org/W2913244614","https://openalex.org/W2938374794","https://openalex.org/W2962893195","https://openalex.org/W2963303028","https://openalex.org/W2963486098","https://openalex.org/W2963499843","https://openalex.org/W2964099675","https://openalex.org/W2966163367","https://openalex.org/W2972539100","https://openalex.org/W2972815379","https://openalex.org/W2972818416","https://openalex.org/W2973094925","https://openalex.org/W2995929068","https://openalex.org/W3007095894","https://openalex.org/W3007328579","https://openalex.org/W3010079431","https://openalex.org/W3030437843","https://openalex.org/W3091787298","https://openalex.org/W3094841848","https://openalex.org/W3097968133","https://openalex.org/W4288102383","https://openalex.org/W4385245566","https://openalex.org/W6767670687","https://openalex.org/W6774379811","https://openalex.org/W6775208754"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1574295218","https://openalex.org/W2061937230","https://openalex.org/W1769849273","https://openalex.org/W113247760","https://openalex.org/W2132885390","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2499802997"],"abstract_inverted_index":{"Acoustic":[0],"models":[1,39,83],"are":[2,89],"susceptible":[3],"to":[4,35,52,84,91,99,107,118,151,155],"the":[5,11,26,113,122,128,156,159,171],"difference":[6],"in":[7],"acoustic":[8],"characteristics":[9],"between":[10],"training":[12],"distribution":[13],"and":[14,25],"test":[15],"distributions.":[16],"Accent":[17],"variability":[18],"is":[19,98,104,173],"a":[20,101,144],"challenging":[21],"source":[22],"of":[23,50,64,70,75,138,149,170],"variability,":[24],"variations":[27],"within":[28],"one":[29],"accent":[30,72],"often":[31,77],"do":[32],"not":[33],"generalize":[34],"others.":[36],"Consequently,":[37],"end-to-end":[38],"that":[40,88,103],"have":[41],"only":[42],"transcriptions":[43],"as":[44],"linguistic":[45,141],"information":[46],"need":[47],"high":[48],"amounts":[49],"data":[51],"learn":[53,85],"how":[54],"different":[55,119],"accents":[56,120],"realize":[57],"their":[58],"sounds.":[59],"To":[60],"aid":[61],"with":[62,143],"recognition":[63],"accented":[65,108],"speech,":[66],"we":[67],"make":[68],"use":[69,137,169],"an":[71,164],"independent":[73],"abstraction":[74],"phonemes,":[76],"called":[78],"metaphonemes.":[79],"We":[80],"force":[81],"our":[82],"hidden":[86],"representations":[87],"correlated":[90],"metaphonemes":[92,172],"using":[93,176],"multi-task":[94],"training.":[95],"Our":[96,125],"aim":[97],"obtain":[100],"model":[102,166],"more":[105],"robust":[106],"speech":[109],"and,":[110],"can,":[111],"at":[112],"same":[114],"time,":[115],"adapt":[116],"faster":[117],"through":[121],"learned":[123],"structure.":[124],"experiments":[126],"on":[127],"Common":[129],"Voice":[130],"corpus":[131],"show":[132],"better":[133],"generalization":[134],"when":[135,153,162],"making":[136,168],"this":[139],"additional":[140],"information,":[142],"word":[145],"error":[146],"rate":[147],"reduction":[148],"up":[150],"12.6%":[152],"compared":[154],"baseline.":[157],"Furthermore,":[158],"relative":[160],"improvement":[161],"adapting":[163],"existing":[165],"by":[167],"higher":[174],"than":[175],"Byte":[177],"Pair":[178],"Encodings":[179],"alone.":[180]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}