{"id":"https://openalex.org/W7116677973","doi":"https://doi.org/10.1109/access.2025.3647153","title":"Sequence-to-Sequence Voice Conversion With Weighted Guided Attention","display_name":"Sequence-to-Sequence Voice Conversion With Weighted Guided Attention","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7116677973","doi":"https://doi.org/10.1109/access.2025.3647153"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3647153","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3647153","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3647153","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085108313","display_name":"Haruki Yamashita","orcid":"https://orcid.org/0009-0001-8553-9317"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haruki Yamashita","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University, Kobe, Japan"],"raw_orcid":"https://orcid.org/0009-0001-8553-9317","affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9913-4647","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109924698","display_name":"Ryoichi Takashima","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Takashima","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Ibaraki, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9808-0250","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Ibaraki, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018533235","display_name":"Yamato Ohtani","orcid":"https://orcid.org/0009-0009-2961-2821"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yamato Ohtani","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0009-0009-2961-2821","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023229059","display_name":"Tetsuya Takiguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Takiguchi","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5005-7679","affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120998763","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0914-5092","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73717012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"216583","last_page":"216595"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9743000268936157,"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":0.9743000268936157,"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":0.007899999618530273,"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/T10863","display_name":"Voice and Speech Disorders","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6546000242233276},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5633000135421753},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.36320000886917114},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.3463999927043915},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.3427000045776367},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.335999995470047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940999865531921},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.677299976348877},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5633000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5095000267028809},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3647153","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3647153","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01257:0007241257","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.14094/0100499601","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3647153","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3647153","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5152828097343445,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G250397299","display_name":null,"funder_award_id":"JPMJBS2410","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"}],"funders":[{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2576309025","https://openalex.org/W2888954148","https://openalex.org/W2897353073","https://openalex.org/W2946555236","https://openalex.org/W2972667718","https://openalex.org/W3015719750","https://openalex.org/W3096567388","https://openalex.org/W3113687514","https://openalex.org/W3118753411","https://openalex.org/W3162512456","https://openalex.org/W3163793923","https://openalex.org/W3196001064","https://openalex.org/W4224612669","https://openalex.org/W4225892118","https://openalex.org/W4297727296","https://openalex.org/W4385245566","https://openalex.org/W4385822333","https://openalex.org/W4385822605","https://openalex.org/W4385823307","https://openalex.org/W4391892412","https://openalex.org/W4392124090","https://openalex.org/W4392904630","https://openalex.org/W4393156644","https://openalex.org/W4402112060","https://openalex.org/W4402112429","https://openalex.org/W4406521093","https://openalex.org/W4412624404"],"related_works":[],"abstract_inverted_index":{"Voice":[0],"conversion":[1,53,108,134],"(VC)":[2],"using":[3,63,103],"non-autoregressive":[4],"sequence-to-sequence":[5],"(S2S)":[6],"models":[7,23],"has":[8],"gained":[9],"attention":[10,80],"in":[11,74],"recent":[12],"years.":[13],"Compared":[14],"with":[15],"conventional":[16,98],"framewise":[17],"VC":[18,22],"models,":[19],"these":[20],"S2S":[21,40],"can":[24],"control":[25],"features,":[26],"such":[27],"as":[28],"prosody":[29],"and":[30,33,36,48,61,82,101,115,132],"speech":[31,114],"speed,":[32],"enable":[34],"high-quality":[35],"fast":[37],"conversion.":[38],"In":[39,55],"VC,":[41],"the":[42,79,86,91,97],"accuracy":[43,135],"of":[44,106],"alignment":[45,87,93],"between":[46],"source":[47],"target":[49],"speakers":[50],"strongly":[51],"affects":[52],"performance.":[54],"this":[56],"paper,":[57],"we":[58],"propose":[59],"EdenVC":[60,66,131],"WSAS-VC":[62,77,102,125],"attention-based":[64],"alignment.":[65],"simply":[67],"introduces":[68],"a":[69],"diagonal-guided":[70],"weighting":[71],"initially":[72],"proposed":[73],"EdenTTS,":[75],"while":[76],"integrates":[78],"weights":[81],"those":[83],"based":[84],"on":[85],"path":[88],"obtained":[89],"from":[90,110,116],"monotonic":[92],"search.":[94],"We":[95],"evaluate":[96],"MAS-VC,":[99],"EdenVC,":[100],"two":[104],"types":[105],"speaker":[107],"conditions,":[109],"native":[111,113,119],"to":[112,118],"non-native":[117],"speech.":[120],"Experimental":[121],"results":[122],"show":[123],"that":[124],"achieves":[126],"more":[127],"stable":[128],"training":[129],"than":[130,136],"better":[133],"MAS-VC.":[137]},"counts_by_year":[],"updated_date":"2025-12-30T23:08:21.542490","created_date":"2025-12-22T00:00:00"}