{"id":"https://openalex.org/W6930833143","doi":"https://doi.org/10.5281/zenodo.14877429","title":"PolySinger: Singing-Voice to Singing-Voice Translation From English to Japanese","display_name":"PolySinger: Singing-Voice to Singing-Voice Translation From English to Japanese","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6930833143","doi":"https://doi.org/10.5281/zenodo.14877429"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877429","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877429","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877429","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Silas Antonisen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Silas Antonisen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Iv\u00e1n L\u00f3pez-Espejo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iv\u00e1n L\u00f3pez-Espejo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.2500999867916107,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.2500999867916107,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.23720000684261322,"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":0.06319999694824219,"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/lyrics","display_name":"Lyrics","score":0.6894000172615051},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5985999703407288},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.454800009727478},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.43810001015663147},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.429500013589859},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4284000098705292}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.6894000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6450999975204468},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5985999703407288},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5769000053405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192999839782715},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.48660001158714294},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28380000591278076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877429","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877429","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877429","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877429","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6518000364303589,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,21,152],"speech":[1],"domain":[2,17],"prevails":[3],"in":[4],"the":[5,15,26,44,48,64,71,82,115,146,191],"spotlight":[6],"for":[7,107,118,179,190],"several":[8,182],"natural":[9],"language":[10],"processing":[11],"(NLP)":[12],"tasks":[13],"while":[14,70],"singing":[16,49],"remains":[18],"less":[19],"explored.":[20],"culmination":[22],"of":[23,36,84,140,154,193],"NLP":[24],"is":[25,60,66,73,105,130,156],"speech-to-speech":[27],"translation":[28,33,58,122],"(S2ST)":[29],"task,":[30],"referring":[31],"to":[32,47,56,93,102,125,132],"and":[34,43,96,110,150,169],"synthesis":[35,78],"human":[37],"speech.":[38],"A":[39,127],"disparity":[40,147],"between":[41,148],"S2ST":[42],"possible":[45],"adaptation":[46],"domain,":[50],"which":[51,142,187],"we":[52],"describe":[53],"as":[54,63],"singing-voice":[55,57],"(SV2SVT),":[59],"becoming":[61],"prominent":[62],"former":[65],"progressing":[67],"ever":[68],"faster,":[69],"latter":[72],"at":[74],"a":[75,134,137,159,176],"standstill.":[76],"Singing-voice":[77],"systems":[79],"are":[80,188],"overcoming":[81],"barrier":[83],"multi-lingual":[85,94],"synthesis,":[86],"despite":[87],"limited":[88],"attention":[89],"has":[90],"been":[91],"paid":[92],"songwriting":[95],"song":[97],"translation.":[98],"This":[99],"paper":[100],"endeavors":[101],"determine":[103],"what":[104],"required":[106],"successful":[108],"SV2SVT":[109,149],"proposes":[111],"PolySinger":[112,155],"(Polyglot":[113],"Singer):":[114],"first":[116],"system":[117],"SV2SVT,":[119,180],"performing":[120],"lyrics":[121],"from":[123],"English":[124],"Japanese.":[126],"cascaded":[128],"approach":[129],"proposed":[131],"establish":[133],"framework":[135],"with":[136,164,172],"high":[138],"degree":[139],"control":[141],"can":[143],"potentially":[144],"diminish":[145],"S2ST.":[151],"performance":[153],"evaluated":[157],"by":[158],"mean":[160],"opinion":[161],"score":[162],"test":[163,173],"native":[165],"Japanese":[166],"speakers.":[167],"Results":[168],"in-depth":[170],"discussions":[171],"subjects":[174],"suggest":[175],"solid":[177],"foundation":[178],"but":[181],"shortcomings":[183],"must":[184],"be":[185],"overcome,":[186],"discussed":[189],"future":[192],"SV2SVT.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
