{"id":"https://openalex.org/W4408351903","doi":"https://doi.org/10.1109/icassp49660.2025.10889744","title":"Investigating Factors Related to the Naturalness of Synthesized Unison Singing","display_name":"Investigating Factors Related to the Naturalness of Synthesized Unison Singing","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351903","doi":"https://doi.org/10.1109/icassp49660.2025.10889744"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":null,"display_name":"Kaito Nishizawa","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaito Nishizawa","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669485","display_name":"Ryuichi Yamamoto","orcid":"https://orcid.org/0000-0003-0299-5470"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichi Yamamoto","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13303","display_name":"Asian Culture and Media Studies","score":0.9702000021934509,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13303","display_name":"Asian Culture and Media Studies","score":0.9702000021934509,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/unison","display_name":"Unison","score":0.9672704935073853},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.9278721809387207},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7260822057723999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5314518213272095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4164658784866333},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21003955602645874},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09405094385147095}],"concepts":[{"id":"https://openalex.org/C2780304638","wikidata":"https://www.wikidata.org/wiki/Q176224","display_name":"Unison","level":2,"score":0.9672704935073853},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9278721809387207},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7260822057723999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5314518213272095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4164658784866333},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21003955602645874},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09405094385147095},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":14,"referenced_works":["https://openalex.org/W2008836807","https://openalex.org/W2145575463","https://openalex.org/W2296704011","https://openalex.org/W2471520273","https://openalex.org/W3187128306","https://openalex.org/W4280575909","https://openalex.org/W4372260026","https://openalex.org/W4391021548","https://openalex.org/W6678318511","https://openalex.org/W6680971021","https://openalex.org/W6712610176","https://openalex.org/W6759107158","https://openalex.org/W6772925044","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2365473327","https://openalex.org/W2096680212","https://openalex.org/W2796195741","https://openalex.org/W2258736945","https://openalex.org/W2016891255","https://openalex.org/W4309134657","https://openalex.org/W4372259973"],"abstract_inverted_index":{"Singing":[0],"voice":[1],"synthesis":[2,14],"(SVS)":[3],"technology":[4],"has":[5,15],"progressed":[6],"rapidly":[7],"in":[8,76,85,98,106],"recent":[9],"years.":[10],"However,":[11],"vocal":[12],"ensemble":[13],"not":[16],"yet":[17],"been":[18],"widely":[19],"explored.":[20],"In":[21],"this":[22],"work,":[23],"we":[24,112],"focus":[25],"on":[26],"unison":[27,54,86,109,118],"singing,":[28],"which":[29],"is":[30,42,102],"to":[31,43,65,81,116],"have":[32],"several":[33],"singers":[34],"singing":[35,87,119],"the":[36,49,52,96,114],"same":[37],"melody":[38],"together.":[39],"Our":[40],"goal":[41],"understand":[44],"what":[45],"acoustic":[46,68],"properties":[47],"affect":[48],"naturalness":[50],"of":[51],"synthesized":[53],"singing.":[55,110],"We":[56],"utilize":[57],"NNSVS,":[58],"an":[59,103,121],"SVS":[60,122],"toolkit":[61],"that":[62,95],"allows":[63],"us":[64],"manipulate":[66],"individual":[67],"features,":[69,75],"including":[70],"timing,":[71],"f0,":[72],"and":[73,100],"spectrum":[74],"a":[77,127],"fully":[78],"data-driven":[79],"manner":[80],"investigate":[82],"their":[83],"effect":[84],"synthesis.":[88],"Through":[89],"listening":[90],"tests,":[91],"it":[92],"was":[93],"shown":[94],"fluctuation":[97],"timing":[99],"f0":[101],"important":[104],"factor":[105],"synthesizing":[107],"natural":[108],"Furthermore,":[111],"discovered":[113],"potential":[115],"generate":[117],"using":[120],"model":[123],"trained":[124],"only":[125],"with":[126],"single":[128],"singer":[129],"dataset.":[130]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
