{"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","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832340","pdf_url":null,"source":null,"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"},"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/A5104262627","display_name":"Hiroaki Hyodo","orcid":null},"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":true,"raw_author_name":"Hiroaki Hyodo","raw_affiliation_strings":["The University of Tokyo,Japan"],"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"},"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"],"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"},"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"],"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"},"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"],"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"},"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"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104262627"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.3862,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71172371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"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":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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","display_name":"Singing","score":0.8652163147926331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6446807384490967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6361306309700012},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2179115116596222}],"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":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832340","pdf_url":null,"source":null,"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2471520273","https://openalex.org/W2519648275","https://openalex.org/W2747070883","https://openalex.org/W2913578941","https://openalex.org/W3007859642","https://openalex.org/W3045884425","https://openalex.org/W3187128306","https://openalex.org/W3190244907","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/W6631190155","https://openalex.org/W6697262704","https://openalex.org/W6746702958","https://openalex.org/W6759107158","https://openalex.org/W6781725382","https://openalex.org/W6782889728","https://openalex.org/W6788137280","https://openalex.org/W6794864843","https://openalex.org/W7043555251"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795"],"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":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
