{"id":"https://openalex.org/W4372260574","doi":"https://doi.org/10.1109/icassp49357.2023.10095773","title":"Modelling Low-Resource Accents Without Accent-Specific TTS Frontend","display_name":"Modelling Low-Resource Accents Without Accent-Specific TTS Frontend","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260574","doi":"https://doi.org/10.1109/icassp49357.2023.10095773"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021310105","display_name":"Georgi Tinchev","orcid":"https://orcid.org/0000-0002-9910-6598"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgi Tinchev","raw_affiliation_strings":["Amazon Research,United Kingdom","Amazon Research, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research,United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon Research, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014060958","display_name":"Marta Czarnowska","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marta Czarnowska","raw_affiliation_strings":["Amazon Research,United Kingdom","Amazon Research, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research,United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon Research, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026378980","display_name":"Kamil Rafa\u0142 Deja","orcid":"https://orcid.org/0000-0003-1156-5544"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Kamil Deja","raw_affiliation_strings":["Warsaw University of Technology,Poland","Warsaw University of Technology, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Warsaw University of Technology,Poland","institution_ids":["https://openalex.org/I108403487"]},{"raw_affiliation_string":"Warsaw University of Technology, Poland","institution_ids":["https://openalex.org/I108403487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kayoko Yanagisawa","raw_affiliation_strings":["Amazon Research,United Kingdom","Amazon Research, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research,United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon Research, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038640628","display_name":"Marius Cotescu","orcid":"https://orcid.org/0000-0001-7005-2920"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marius Cotescu","raw_affiliation_strings":["Amazon Research,United Kingdom","Amazon Research, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research,United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon Research, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8712,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73065264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9950000047683716,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9907000064849854,"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/stress","display_name":"Stress (linguistics)","score":0.7859096527099609},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6169723272323608},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5744917392730713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3885815739631653},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10898146033287048}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7859096527099609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6169723272323608},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5744917392730713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3885815739631653},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10898146033287048}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1505652865","https://openalex.org/W1524333225","https://openalex.org/W1593247906","https://openalex.org/W1928942490","https://openalex.org/W1989826161","https://openalex.org/W1991682319","https://openalex.org/W2017742648","https://openalex.org/W2124331435","https://openalex.org/W2157259375","https://openalex.org/W2262393948","https://openalex.org/W2514457011","https://openalex.org/W2795109282","https://openalex.org/W2888797456","https://openalex.org/W2890402938","https://openalex.org/W2955237921","https://openalex.org/W2962788625","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2973142754","https://openalex.org/W2983786745","https://openalex.org/W3015282541","https://openalex.org/W3015430779","https://openalex.org/W3135654121","https://openalex.org/W3150435369","https://openalex.org/W3162508345","https://openalex.org/W3162770051","https://openalex.org/W3195171908","https://openalex.org/W3197558340","https://openalex.org/W3204009030","https://openalex.org/W4240592325","https://openalex.org/W4283824751","https://openalex.org/W4283837596","https://openalex.org/W4295731579","https://openalex.org/W4296069158","https://openalex.org/W4296069283","https://openalex.org/W4319862665","https://openalex.org/W4394150413","https://openalex.org/W6631362777","https://openalex.org/W6683276001","https://openalex.org/W6794002749","https://openalex.org/W6890269780"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4367680763","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W4213177143","https://openalex.org/W2151922127","https://openalex.org/W4237818736","https://openalex.org/W4252005663","https://openalex.org/W2365914832"],"abstract_inverted_index":{"This":[0],"work":[1,23,132],"focuses":[2],"on":[3,24,78,163],"modelling":[4,25],"a":[5,12,18,28,73,101,110],"speaker\u2019s":[6],"accent":[7,60],"that":[8,134],"does":[9],"not":[10,39],"have":[11],"dedicated":[13],"text-to-speech":[14],"(TTS)":[15],"frontend,":[16],"including":[17],"grapheme-to-phoneme":[19],"(G2P)":[20],"module.":[21],"Prior":[22],"accents":[26,137,160],"assumes":[27],"phonetic":[29],"transcription":[30],"is":[31],"available":[32,162],"for":[33,43,105],"the":[34,41,58,65,79,88,93,97,106,120],"target":[35,59,94],"accent,":[36],"which":[37],"might":[38],"be":[40,139],"case":[42],"low-resource,":[44],"regional":[45],"accents.":[46],"In":[47],"our":[48,155,164],"work,":[49],"we":[50,55,99],"propose":[51],"an":[52,148],"approach":[53],"whereby":[54],"first":[56],"augment":[57],"data":[61,144],"to":[62,86,127,158],"sound":[63],"like":[64],"donor":[66],"voice":[67,69,90],"via":[68],"conversion,":[70],"then":[71],"train":[72],"multi-speaker":[74],"multi-accent":[75],"TTS":[76,102,150],"model":[77,156],"combination":[80],"of":[81,154],"recordings":[82],"and":[83,116,145],"synthetic":[84],"data,":[85],"generate":[87],"donor\u2019s":[89],"speaking":[91],"in":[92],"accent.":[95,112],"Throughout":[96],"procedure,":[98],"use":[100],"frontend":[103],"developed":[104],"same":[107],"language":[108],"but":[109],"different":[111],"We":[113],"show":[114],"qualitative":[115],"quantitative":[117],"analysis":[118],"where":[119],"proposed":[121],"strategy":[122],"achieves":[123],"state-of-the-art":[124],"results":[125],"compared":[126],"other":[128],"generative":[129],"models.":[130],"Our":[131],"demonstrates":[133],"low":[135],"resource":[136],"can":[138],"modelled":[140],"with":[141],"relatively":[142],"little":[143],"without":[146],"developing":[147],"accent-specific":[149],"frontend.":[151],"Audio":[152],"samples":[153],"converting":[157],"multiple":[159],"are":[161],"web":[165],"page3.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}