{"id":"https://openalex.org/W4323339216","doi":"https://doi.org/10.1109/snpd54884.2022.10051811","title":"StyleFormerGAN-VC:Improving Effect of few shot Cross-Lingual Voice Conversion Using VAE-StarGAN and Attention-AdaIN","display_name":"StyleFormerGAN-VC:Improving Effect of few shot Cross-Lingual Voice Conversion Using VAE-StarGAN and Attention-AdaIN","publication_year":2022,"publication_date":"2022-12-07","ids":{"openalex":"https://openalex.org/W4323339216","doi":"https://doi.org/10.1109/snpd54884.2022.10051811"},"language":"en","primary_location":{"id":"doi:10.1109/snpd54884.2022.10051811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd54884.2022.10051811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACIS 23rd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","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/A5102845007","display_name":"Dengfeng Ke","orcid":"https://orcid.org/0000-0001-8459-0412"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dengfeng Ke","raw_affiliation_strings":["School of Information Science, Beijing Language and Culture University,Beijing,China","School of Information Science, Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001927761","display_name":"Wenhan Yao","orcid":"https://orcid.org/0000-0003-1014-9565"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Yao","raw_affiliation_strings":["School of Information Science, Beijing Language and Culture University,Beijing,China","School of Information Science, Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076551862","display_name":"Ruixin Hu","orcid":"https://orcid.org/0000-0002-0999-0712"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixin Hu","raw_affiliation_strings":["School of Information Science, Beijing Language and Culture University,Beijing,China","School of Information Science, Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068030070","display_name":"Liangjie Huang","orcid":"https://orcid.org/0000-0003-0770-1582"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangjie Huang","raw_affiliation_strings":["School of Information Science, Beijing Language and Culture University,Beijing,China","School of Information Science, Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057554364","display_name":"Qi Luo","orcid":"https://orcid.org/0009-0000-8290-5441"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Luo","raw_affiliation_strings":["School of Information Science, Beijing Language and Culture University,Beijing,China","School of Information Science, Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005711805","display_name":"Wentao Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Shu","raw_affiliation_strings":["School of Information Science, Beijing Language and Culture University,Beijing,China","School of Information Science, Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102845007"],"corresponding_institution_ids":["https://openalex.org/I115212828"],"apc_list":null,"apc_paid":null,"fwci":0.3979,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68372473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"235","last_page":"239"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9962999820709229,"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/utterance","display_name":"Utterance","score":0.7874739170074463},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7751039862632751},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7501565217971802},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5243130922317505},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5156527757644653},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.48780563473701477},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4772324860095978},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4544442594051361},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.45078176259994507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4081486761569977},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08404609560966492},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0834243893623352}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7874739170074463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751039862632751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7501565217971802},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5243130922317505},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5156527757644653},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.48780563473701477},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4772324860095978},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4544442594051361},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.45078176259994507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4081486761569977},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08404609560966492},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0834243893623352},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/snpd54884.2022.10051811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd54884.2022.10051811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACIS 23rd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2284050935","https://openalex.org/W2774848319","https://openalex.org/W2903739847","https://openalex.org/W2936718374","https://openalex.org/W2937579788","https://openalex.org/W2951595529","https://openalex.org/W2963539064","https://openalex.org/W2965685620","https://openalex.org/W2972544500","https://openalex.org/W2972659941","https://openalex.org/W3007502375","https://openalex.org/W3033411150","https://openalex.org/W3082130377","https://openalex.org/W3092028330","https://openalex.org/W3162427973","https://openalex.org/W3162512456","https://openalex.org/W3162879338","https://openalex.org/W3163271138","https://openalex.org/W3196667132","https://openalex.org/W3198533616","https://openalex.org/W4224309976","https://openalex.org/W4225939199","https://openalex.org/W4296068587","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638836233","https://openalex.org/W6695676441","https://openalex.org/W6746801104","https://openalex.org/W6776390925","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6810889627","https://openalex.org/W6840412704"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2529301793","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W2384121599","https://openalex.org/W3109975354"],"abstract_inverted_index":{"Voice":[0],"Conversion":[1],"(VC)":[2],"aims":[3],"to":[4,49,61,75,89,95],"transfer":[5],"the":[6,11,15,47,63,67,77,84,109],"speaker":[7,97],"timbre":[8],"while":[9],"retaining":[10],"lexical":[12],"content":[13],"of":[14,66],"source":[16],"speech":[17,54,78],"and":[18,70,87,112],"has":[19],"attracted":[20],"much":[21],"attention":[22],"lately.":[23],"Although":[24],"previous":[25],"VC":[26],"models":[27],"have":[28],"achieved":[29],"good":[30],"performance,":[31],"unstability":[32],"can":[33],"not":[34],"be":[35],"avoided":[36],"when":[37],"it":[38],"comes":[39],"cross-lingual":[40,68,110],"scenario.":[41],"In":[42,80],"this":[43],"paper,":[44],"we":[45,82],"propose":[46],"StyleFormerGAN-VC":[48],"achieve":[50],"better":[51],"cross":[52],"language":[53],"conversion,":[55],"where":[56],"variational":[57],"auto-encoder":[58],"is":[59,73],"introduced":[60],"model":[62,92,105],"feature":[64],"distribution":[65],"utterances":[69],"adversarial":[71],"training":[72],"applied":[74],"elevate":[76],"quality.":[79],"addition,":[81],"combine":[83],"Attention":[85],"mechanism":[86],"AdaIN":[88],"make":[90],"our":[91,104],"more":[93],"generalized":[94],"unseen":[96],"with":[98],"long":[99],"utterance.":[100],"Experiments":[101],"show":[102],"that":[103],"performs":[106],"stably":[107],"in":[108],"scenario":[111],"gains":[113],"well":[114],"MOS":[115],"evaluation":[116],"scores.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
