{"id":"https://openalex.org/W4392910800","doi":"https://doi.org/10.1109/icassp48485.2024.10447205","title":"Transfer the Linguistic Representations from TTS to Accent Conversion with Non-Parallel Data","display_name":"Transfer the Linguistic Representations from TTS to Accent Conversion with Non-Parallel Data","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910800","doi":"https://doi.org/10.1109/icassp48485.2024.10447205"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5081740800","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-8057-4623"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China","School of Data Science, The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113092681","display_name":"Jiakun Pei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiakun Pei","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China","School of Data Science, The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009337933","display_name":"Liumeng Xue","orcid":"https://orcid.org/0000-0003-2815-8494"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liumeng Xue","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China","School of Data Science, The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070281927","display_name":"Mingyang Zhang","orcid":"https://orcid.org/0000-0002-7945-0535"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China","School of Data Science, The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12501","last_page":"12505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9678999781608582,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9678999781608582,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9534000158309937,"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/T10028","display_name":"Topic Modeling","score":0.9337000250816345,"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":0.6999669075012207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6663424372673035},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5990511178970337},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5342817306518555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4634769856929779},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38421744108200073},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08045580983161926}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6999669075012207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6663424372673035},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5990511178970337},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5342817306518555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634769856929779},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38421744108200073},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08045580983161926}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1892640180","https://openalex.org/W2395237272","https://openalex.org/W2888954148","https://openalex.org/W2890402938","https://openalex.org/W2972359262","https://openalex.org/W2972970915","https://openalex.org/W2973142754","https://openalex.org/W3015430779","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3178546316","https://openalex.org/W3204009030","https://openalex.org/W4287776895","https://openalex.org/W4296069266","https://openalex.org/W4297841851","https://openalex.org/W4367032484","https://openalex.org/W4372266858","https://openalex.org/W4385245566","https://openalex.org/W4385823191","https://openalex.org/W6777327638","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6847363464"],"related_works":["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","https://openalex.org/W2352261042","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Accent":[0],"conversion":[1,29,67],"aims":[2],"to":[3,11,38,103],"convert":[4,39],"the":[5,17,40,43,47,64,75,105,114,117,121],"accent":[6,28,41,65],"of":[7,63,77,107,116,123],"a":[8,12,23,78,94],"source":[9,44],"speech":[10,51],"target":[13],"accent,":[14],"meanwhile":[15],"preserving":[16],"speaker\u2019s":[18],"identity.":[19],"This":[20],"paper":[21],"introduces":[22],"novel":[24],"non-autoregressive":[25],"framework":[26],"for":[27],"that":[30],"learns":[31],"accent-agnostic":[32],"linguistic":[33,54],"representations":[34,52,55],"and":[35,84,100,120,133],"employs":[36],"them":[37],"in":[42,128],"speech.":[45],"Specifically,":[46],"proposed":[48,90],"system":[49],"aligns":[50],"with":[53],"obtained":[56],"from":[57],"Text-to-Speech":[58],"(TTS)":[59],"systems,":[60],"enabling":[61],"training":[62],"voice":[66],"model":[68],"on":[69,81],"non-parallel":[70],"data.":[71],"Furthermore,":[72],"we":[73],"investigate":[74],"effectiveness":[76],"pretraining":[79,118],"strategy":[80,119],"native":[82],"data":[83],"different":[85],"acoustic":[86],"features":[87],"within":[88],"our":[89,108],"framework.":[91],"We":[92],"conduct":[93],"comprehensive":[95],"evaluation":[96,111],"using":[97],"both":[98],"subjective":[99],"objective":[101],"metrics":[102],"assess":[104],"performance":[106],"approach.":[109],"The":[110],"results":[112],"highlight":[113],"benefits":[115],"incorporation":[122],"richer":[124],"semantic":[125],"features,":[126],"resulting":[127],"significantly":[129],"enhanced":[130],"audio":[131],"quality":[132],"intelligibility":[134],"<sup":[135],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[136],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[137],".":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}