{"id":"https://openalex.org/W4406461964","doi":"https://doi.org/10.1109/slt61566.2024.10832340","title":"DNN-Based Ensemble Singing Voice Synthesis With Interactions Between Singers","display_name":"DNN-Based Ensemble Singing Voice Synthesis With Interactions Between Singers","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461964","doi":"https://doi.org/10.1109/slt61566.2024.10832340"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832340","doi":"https://doi.org/10.1109/slt61566.2024.10832340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832340","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.09988","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104262627","display_name":"Hiroaki Hyodo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroaki Hyodo","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847","observed_orcids":["https://orcid.org/0000-0003-0520-7847"]},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["Keio University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941659","display_name":"Tomohiko Nakamura","orcid":"https://orcid.org/0000-0003-4385-7170","observed_orcids":["https://orcid.org/0000-0003-4385-7170"]},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiko Nakamura","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041787266","display_name":"Junya Koguchi","orcid":"https://orcid.org/0009-0007-0682-1546","observed_orcids":["https://orcid.org/0009-0007-0682-1546"]},"institutions":[{"id":"https://openalex.org/I16656306","display_name":"Meiji University","ror":"https://ror.org/02rqvrp93","country_code":"JP","type":"education","lineage":["https://openalex.org/I16656306"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junya Koguchi","raw_affiliation_strings":["Meiji University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meiji University,Japan","institution_ids":["https://openalex.org/I16656306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617","observed_orcids":["https://orcid.org/0000-0003-0876-5617"]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3054,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50447172,"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":"660","last_page":"667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.4189000129699707,"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":0.4189000129699707,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.3303000032901764,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.21770000457763672,"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/singing-voice-synthesis","display_name":"singing voice synthesis","score":0.996999979019165},{"id":"https://openalex.org/keywords/ensemble-singing","display_name":"ensemble singing","score":0.9580000042915344},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.6880000233650208},{"id":"https://openalex.org/keywords/vocal-harmony","display_name":"vocal harmony","score":0.4410000145435333},{"id":"https://openalex.org/keywords/acoustic-characteristics","display_name":"acoustic features","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8652163147926331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6446807384490967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6361306309700012},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2179115116596222},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt61566.2024.10832340","doi":"https://doi.org/10.1109/slt61566.2024.10832340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832340","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.09988","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.09988","pdf_url":"https://arxiv.org/pdf/2409.09988","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.09988","doi":"https://doi.org/10.48550/arxiv.2409.09988","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.09988","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.09988","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.09988","pdf_url":"https://arxiv.org/pdf/2409.09988","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2043344473","display_name":"Singing voice synthesis that can form ensemble with humans and computers","funder_award_id":"23K18474","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4513544307","display_name":null,"funder_award_id":"JPMJFR226V","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7231568964","display_name":"\u4eba\u9593\u306e\u4ecb\u5165\u53ef\u80fd\u6027\u3092\u8003\u616e\u3057\u305f\u97f3\u97ff\u60c5\u666f\u5206\u6790\u306e\u305f\u3081\u306e\u6df1\u5c64\u5206\u6790\u5408\u6210\u57fa\u76e4\u306e\u958b\u62d3\u3068\u305d\u306e\u6df1\u5316","funder_award_id":"23K28108","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406461964.pdf","grobid_xml":"https://content.openalex.org/works/W4406461964.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2293847077","https://openalex.org/W2471520273","https://openalex.org/W2519648275","https://openalex.org/W2747070883","https://openalex.org/W2774637732","https://openalex.org/W2913578941","https://openalex.org/W2915654580","https://openalex.org/W2989824594","https://openalex.org/W3007859642","https://openalex.org/W3045884425","https://openalex.org/W3071390758","https://openalex.org/W3116770123","https://openalex.org/W3158762648","https://openalex.org/W3187128306","https://openalex.org/W3198508974","https://openalex.org/W3207340675","https://openalex.org/W4226153886","https://openalex.org/W4372259973","https://openalex.org/W4372260026","https://openalex.org/W4372338328","https://openalex.org/W4375869200","https://openalex.org/W6782889728"],"related_works":["https://openalex.org/W4408351903","https://openalex.org/W4290647479","https://openalex.org/W4221167708","https://openalex.org/W7128516282","https://openalex.org/W4372190416","https://openalex.org/W4221155333","https://openalex.org/W3095074555","https://openalex.org/W4404146721","https://openalex.org/W7143897755","https://openalex.org/W4387968499"],"abstract_inverted_index":{"We":[0],"propose":[1,70],"a":[2,9,27,71],"singing":[3,13,54],"voice":[4,14,41,89],"synthesis":[5],"(SVS)":[6],"method":[7],"for":[8],"more":[10],"unified":[11],"ensemble":[12,50],"by":[15],"modeling":[16],"interactions":[17,34],"between":[18,35],"singers.":[19],"Most":[20],"existing":[21],"SVS":[22,72],"methods":[23,107],"aim":[24],"to":[25,42,99],"synthesize":[26],"solo":[28,53],"voice,":[29],"and":[30,91],"do":[31],"not":[32],"consider":[33],"singers,":[36],"i.e.,":[37],"adjusting":[38],"one\u2019s":[39],"own":[40],"the":[43,47,57,62,65,75,96,109,112],"others\u2019":[44],"voices.":[45],"Since":[46],"production":[48],"of":[49,64,87,111],"voices":[51,55],"from":[52],"ignores":[56],"interactions,":[58],"it":[59],"can":[60],"degrade":[61],"unity":[63,110],"vocal":[66,113],"ensemble.":[67,114],"Therefore,":[68],"we":[69],"that":[73,83,94,105],"reproduces":[74],"interactions.":[76],"It":[77],"is":[78],"based":[79],"on":[80],"an":[81],"architecture":[82],"uses":[84],"musical":[85],"scores":[86],"multiple":[88],"parts,":[90],"loss":[92],"functions":[93],"simulate":[95],"interactions\u2019":[97],"effect":[98],"acoustic":[100],"features.":[101],"Experimental":[102],"results":[103],"show":[104],"our":[106],"improve":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-01-17T00:00:00"}
