{"id":"https://openalex.org/W4393380352","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10476833","title":"Zero Shot Text to Speech Augmentation for Automatic Speech Recognition on Low-Resource Accented Speech Corpora","display_name":"Zero Shot Text to Speech Augmentation for Automatic Speech Recognition on Low-Resource Accented Speech Corpora","publication_year":2023,"publication_date":"2023-10-29","ids":{"openalex":"https://openalex.org/W4393380352","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10476833"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf59524.2023.10476833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59524.2023.10476833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-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/A5015387266","display_name":"Francesco Nespoli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Francesco Nespoli","raw_affiliation_strings":["Microsoft","Imperial College, London"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Imperial College, London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028299110","display_name":"Daniel R. Barreda","orcid":"https://orcid.org/0000-0003-4630-2840"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel Barreda","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Imperial College,London","Imperial College, London"],"affiliations":[{"raw_affiliation_string":"Imperial College,London","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College, London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015387266"],"corresponding_institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.1746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60649504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1080","last_page":"1084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9929999709129333,"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":0.9929999709129333,"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":0.9564999938011169,"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/speech-recognition","display_name":"Speech recognition","score":0.7632968425750732},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7384046316146851},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5963436365127563},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5328125953674316},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5321224331855774},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4607217609882355},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4601185619831085},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44384831190109253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4298301637172699},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4234396517276764},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19165295362472534}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7632968425750732},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384046316146851},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5963436365127563},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5328125953674316},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5321224331855774},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4607217609882355},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4601185619831085},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44384831190109253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4298301637172699},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4234396517276764},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19165295362472534},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf59524.2023.10476833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59524.2023.10476833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2696967604","https://openalex.org/W2936774411","https://openalex.org/W2990138404","https://openalex.org/W3015430779","https://openalex.org/W3026874504","https://openalex.org/W3090254849","https://openalex.org/W3160475509","https://openalex.org/W3167533889","https://openalex.org/W3173715137","https://openalex.org/W3201401182","https://openalex.org/W3203561692","https://openalex.org/W4323207641","https://openalex.org/W6777694618","https://openalex.org/W6783867762","https://openalex.org/W6790915370","https://openalex.org/W6796464841","https://openalex.org/W6802503112","https://openalex.org/W6805710207","https://openalex.org/W6850752909"],"related_works":["https://openalex.org/W596245619","https://openalex.org/W2036933852","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2550171623","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W1987021544","https://openalex.org/W2009814707"],"abstract_inverted_index":{"In":[0,141],"recent":[1],"years,":[2],"automatic":[3],"speech":[4,90,110,172],"recognition":[5],"(ASR)":[6],"models":[7],"greatly":[8],"improved":[9],"transcription":[10],"performance":[11,52,125,162],"both":[12],"in":[13,20,39,76,81,124],"clean,":[14],"low":[15],"noise,":[16],"acoustic":[17,41,66],"conditions":[18],"and":[19],"reverberant":[21],"environments.":[22],"However,":[23],"all":[24],"these":[25],"systems":[26],"rely":[27],"on":[28,92,103,130,169],"the":[29,51,54,77,86,108,122,127,157],"availability":[30],"of":[31,33,35,53,72,88,126,151],"hundreds":[32],"hours":[34],"labelled":[36],"training":[37,46,78],"data":[38,91,132],"specific":[40,65],"conditions.":[42],"When":[43],"such":[44],"a":[45,64,69,100,148,165],"dataset":[47],"is":[48,56,74,118],"not":[49],"available,":[50],"system":[55,129,159],"heavily":[57],"impacted.":[58],"For":[59],"example,":[60],"this":[61,82,115],"happens":[62],"when":[63],"environment":[67],"or":[68],"particular":[70],"population":[71],"speakers":[73],"under-represented":[75],"dataset.":[79],"Specifically,":[80],"paper":[83],"we":[84,98,143],"investigate":[85],"effect":[87],"accented":[89,109,131,171],"an":[93],"off-the-shelf":[94],"ASR":[95,128,158],"system.":[96],"Furthermore,":[97],"suggest":[99],"strategy":[101],"based":[102],"zero-shot":[104],"text-to-speech":[105],"to":[106,120,134,164,175],"augment":[107],"corpora.":[111],"We":[112],"show":[113],"that":[114,145],"augmentation":[116],"method":[117],"able":[119],"mitigate":[121],"loss":[123],"up":[133,174],"5%":[135],"word":[136],"error":[137],"rate":[138],"reduction":[139],"(WERR).":[140],"conclusion,":[142],"demonstrate":[144],"by":[146],"incorporating":[147],"modest":[149],"fraction":[150],"real":[152],"with":[153,173],"synthetically":[154],"generated":[155],"data,":[156],"exhibits":[160],"superior":[161],"compared":[163],"model":[166],"trained":[167],"exclusively":[168],"authentic":[170],"14%":[176],"WERR.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}