{"id":"https://openalex.org/W4405709481","doi":"https://doi.org/10.1109/iscslp63861.2024.10800623","title":"Diffusion-Based Method with TTS Guidance for Foreign Accent Conversion","display_name":"Diffusion-Based Method with TTS Guidance for Foreign Accent Conversion","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709481","doi":"https://doi.org/10.1109/iscslp63861.2024.10800623"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5061759376","display_name":"Qibing Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qibing Bai","raw_affiliation_strings":["School of Data Science"],"affiliations":[{"raw_affiliation_string":"School of Data Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328264","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-0866-0308"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["School of Data Science"],"affiliations":[{"raw_affiliation_string":"School of Data Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425923","display_name":"Zhijun Liu","orcid":"https://orcid.org/0000-0001-5533-3038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhijun Liu","raw_affiliation_strings":["School of Data Science"],"affiliations":[{"raw_affiliation_string":"School of Data Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070281927","display_name":"Mingyang Zhang","orcid":"https://orcid.org/0000-0002-7945-0535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyang Zhang","raw_affiliation_strings":["School of Data Science"],"affiliations":[{"raw_affiliation_string":"School of Data Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072851763","display_name":"Wei Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":["Tencent Ethereal Audio Lab, Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084128157","display_name":"Yannan Wang","orcid":"https://orcid.org/0000-0001-7248-4954"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yannan Wang","raw_affiliation_strings":["Tencent Ethereal Audio Lab, Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["School of Data Science"],"affiliations":[{"raw_affiliation_string":"School of Data Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5061759376"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1134,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42726706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"284","last_page":"288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10592","display_name":"Fusion materials and technologies","score":0.0494999997317791,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10592","display_name":"Fusion materials and technologies","score":0.0494999997317791,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10572","display_name":"Geophysical and Geoelectrical Methods","score":0.04910000041127205,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.030700000002980232,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7874773144721985},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.637511134147644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.614690363407135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3397933840751648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3227006196975708},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06503161787986755}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7874773144721985},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.637511134147644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614690363407135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3397933840751648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3227006196975708},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06503161787986755},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1892640180","https://openalex.org/W1991682319","https://openalex.org/W2017742648","https://openalex.org/W2023728986","https://openalex.org/W2143076222","https://openalex.org/W2507912506","https://openalex.org/W2747874407","https://openalex.org/W2888954148","https://openalex.org/W2890402938","https://openalex.org/W2963609956","https://openalex.org/W2972970915","https://openalex.org/W2973142754","https://openalex.org/W3015430779","https://openalex.org/W3150572638","https://openalex.org/W3178546316","https://openalex.org/W3198213150","https://openalex.org/W3204009030","https://openalex.org/W4243859118","https://openalex.org/W4281736089","https://openalex.org/W4296069266","https://openalex.org/W4297841851","https://openalex.org/W4367032484","https://openalex.org/W4372266858","https://openalex.org/W4385245566","https://openalex.org/W4385822967","https://openalex.org/W4385823191","https://openalex.org/W4388821525","https://openalex.org/W4388979610","https://openalex.org/W4390872297","https://openalex.org/W4392910800","https://openalex.org/W4392931276","https://openalex.org/W4402111808","https://openalex.org/W6777327638","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6795261426","https://openalex.org/W6846539466","https://openalex.org/W6847363464","https://openalex.org/W6868957684","https://openalex.org/W6869691399"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","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"],"abstract_inverted_index":{"Accent":[0],"conversion":[1,30,49,60,84],"(AC)":[2],"aims":[3],"to":[4,41,46,58],"alter":[5],"the":[6,13,65,80,96,102,106],"accent":[7,21,29,59,83],"of":[8,110],"spoken":[9],"language":[10],"while":[11],"preserving":[12],"original":[14],"content":[15],"and":[16,64,86,114],"speaker":[17,54,115],"characteristics.":[18],"While":[19],"any":[20],"can":[22],"be":[23],"selected":[24],"as":[25],"a":[26,76,88],"target,":[27],"foreign":[28],"(FAC)":[31],"that":[32,101],"focuses":[33],"on":[34,53,95],"L2":[35],"speakers":[36],"is":[37,61,68],"particularly":[38],"noteworthy":[39],"due":[40],"its":[42],"wide-ranging":[43],"applications.":[44],"Compared":[45],"general":[47],"voice":[48],"tasks,":[50],"which":[51],"focus":[52],"conversion,":[55],"research":[56],"related":[57],"relatively":[62],"scarce,":[63],"audio":[66],"quality":[67],"often":[69],"limited.":[70],"In":[71],"this":[72],"article,":[73],"we":[74],"introduce":[75],"diffusion":[77],"decoder":[78],"into":[79],"conventional":[81],"TTS-guided":[82],"framework":[85],"propose":[87],"phoneme-level":[89],"acoustic-linguistic":[90],"alignment":[91],"strategy.":[92],"Subjective":[93],"evaluations":[94],"Chinese-accent":[97],"source":[98],"speech":[99,111],"confirm":[100],"proposed":[103],"method":[104],"outperforms":[105],"baseline":[107],"in":[108],"terms":[109],"naturalness,":[112],"accentedness,":[113],"similarity<sup":[116],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[117,119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[118],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Audio":[120],"samples":[121],"are":[122],"available":[123],"at":[124],"diff-fac.github.io..":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}