{"id":"https://openalex.org/W3198530659","doi":"https://doi.org/10.21437/interspeech.2021-506","title":"Two-Pathway Style Embedding for Arbitrary Voice Conversion","display_name":"Two-Pathway Style Embedding for Arbitrary Voice Conversion","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198530659","doi":"https://doi.org/10.21437/interspeech.2021-506","mag":"3198530659"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-506","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5081820690","display_name":"Xuexin Xu","orcid":"https://orcid.org/0000-0003-0055-4882"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuexin Xu","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102763475","display_name":"Liang Shi","orcid":"https://orcid.org/0009-0009-4551-3292"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Shi","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627380","display_name":"Jinhui Chen","orcid":"https://orcid.org/0000-0002-3701-9026"},"institutions":[{"id":"https://openalex.org/I122146667","display_name":"Prefectural University of Hiroshima","ror":"https://ror.org/0059h1f24","country_code":"JP","type":"education","lineage":["https://openalex.org/I122146667"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jinhui Chen","raw_affiliation_strings":["Prefectural University of Hiroshima, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prefectural University of Hiroshima, Japan","institution_ids":["https://openalex.org/I122146667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065285274","display_name":"Xunquan Chen","orcid":"https://orcid.org/0000-0002-5336-6386"},"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":"Xunquan Chen","raw_affiliation_strings":["Kobe University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618323","display_name":"Jie Lian","orcid":"https://orcid.org/0000-0002-9752-8260"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Lian","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077415759","display_name":"Pingyuan Lin","orcid":"https://orcid.org/0009-0007-7510-8859"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingyuan Lin","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419458","display_name":"Zhihong Zhang","orcid":"https://orcid.org/0000-0002-0542-0640"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihong Zhang","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074364400","display_name":"Edwin R. Hancock","orcid":"https://orcid.org/0000-0003-4496-2028"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Edwin R. Hancock","raw_affiliation_strings":["University of York, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of York, United Kingdom","institution_ids":["https://openalex.org/I52099693"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100419458"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1364","last_page":"1368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9983999729156494,"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":0.9779000282287598,"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/computer-science","display_name":"Computer science","score":0.7501482963562012},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6809958815574646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6695317625999451},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6123644709587097},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5345522165298462},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5023477077484131},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45185959339141846},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4342436194419861},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4231102168560028},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33851778507232666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31627029180526733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501482963562012},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6809958815574646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6695317625999451},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6123644709587097},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5345522165298462},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5023477077484131},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45185959339141846},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4342436194419861},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4231102168560028},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33851778507232666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31627029180526733},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-506","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:177842","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1588037970","https://openalex.org/W1901129140","https://openalex.org/W1959608418","https://openalex.org/W2017742648","https://openalex.org/W2056852181","https://openalex.org/W2148846882","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2502312327","https://openalex.org/W2603777577","https://openalex.org/W2804998325","https://openalex.org/W2902070858","https://openalex.org/W2945478979","https://openalex.org/W2962896155","https://openalex.org/W2963539064","https://openalex.org/W2963609956","https://openalex.org/W2963830550","https://openalex.org/W2969803502","https://openalex.org/W2970006822","https://openalex.org/W2972544500","https://openalex.org/W2972659941","https://openalex.org/W2972667718","https://openalex.org/W2972689158","https://openalex.org/W3015434413","https://openalex.org/W3096524539","https://openalex.org/W3096558818","https://openalex.org/W4295521014","https://openalex.org/W4320013936","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2124576126","https://openalex.org/W2138455584","https://openalex.org/W1984264321","https://openalex.org/W3109975354","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869","https://openalex.org/W2597655663"],"abstract_inverted_index":{"Arbitrary":[0],"voice":[1,8,34,170],"conversion,":[2,9,35],"also":[3],"referred":[4],"to":[5,31,40,42,90,103,137],"as":[6],"zero-shot":[7,33,169],"has":[10],"recently":[11],"attracted":[12],"increased":[13],"attention":[14,99],"in":[15,65],"the":[16,19,36,51,57,105,124,139,161,165],"literature.Although":[17],"disentangling":[18],"linguistic":[20],"and":[21,56,80,94,111,150],"style":[22,46,96,110,118,132,141],"representations":[23],"for":[24,78,108],"acoustic":[25],"features":[26],"is":[27,47,89,101,151],"an":[28],"effective":[29],"way":[30],"achieve":[32],"problem":[37],"of":[38,50,54,59,86,127,130],"how":[39],"convert":[41],"a":[43,70,116,134],"natural":[44,81],"speaker":[45],"challenging":[48],"because":[49],"intrinsic":[52],"variabilities":[53],"speech":[55,82,156],"difficulties":[58],"completely":[60],"decoupling":[61],"them.For":[62],"this":[63,66,87],"reason,":[64],"paper,":[67],"we":[68,121],"propose":[69],"Two-Pathway":[71],"Style":[72],"Embedding":[73],"Voice":[74],"Conversion":[75],"framework":[76],"(TPSE-VC)":[77],"realistic":[79],"conversion.The":[83],"novel":[84,98],"feature":[85],"method":[88],"simultaneously":[91],"embed":[92],"sentence-level":[93,140],"phoneme-level":[95,117],"information.A":[97],"mechanism":[100],"proposed":[102,162],"implement":[104],"implicit":[106],"alignment":[107],"timbre":[109],"phoneme":[112],"content,":[113],"further":[114],"embedding":[115,123],"representation.In":[119],"addition,":[120],"consider":[122],"complete":[125],"set":[126],"time":[128],"steps":[129],"audio":[131],"into":[133],"fixed-length":[135],"vector":[136],"obtain":[138],"representation.Moreover,":[142],"TPSE-VC":[143,163],"does":[144],"not":[145],"require":[146],"any":[147],"pre-trained":[148],"models,":[149],"only":[152],"trained":[153],"with":[154],"non-parallel":[155],"data.Experimental":[157],"results":[158,167],"demonstrate":[159],"that":[160],"outperforms":[164],"state-of-theart":[166],"on":[168],"conversion.":[171]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}