{"id":"https://openalex.org/W2982290989","doi":"https://doi.org/10.1109/icassp40776.2020.9054636","title":"Disentangling Timbre and Singing Style with Multi-Singer Singing Synthesis System","display_name":"Disentangling Timbre and Singing Style with Multi-Singer Singing Synthesis System","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982290989","doi":"https://doi.org/10.1109/icassp40776.2020.9054636","mag":"2982290989"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.13069","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065510735","display_name":"Juheon Lee","orcid":"https://orcid.org/0000-0003-4516-8766"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Juheon Lee","raw_affiliation_strings":["Music and Audio Research Group, Seoul National University","Seoul National University,Music and Audio Research Group"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University,Music and Audio Research Group","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091245121","display_name":"Hyeong-Seok Choi","orcid":"https://orcid.org/0000-0001-6494-7736"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeong-Seok Choi","raw_affiliation_strings":["Music and Audio Research Group, Seoul National University","Seoul National University,Music and Audio Research Group"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University,Music and Audio Research Group","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031164776","display_name":"Junghyun Koo","orcid":"https://orcid.org/0009-0004-4468-0367"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junghyun Koo","raw_affiliation_strings":["Music and Audio Research Group, Seoul National University","Seoul National University,Music and Audio Research Group"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University,Music and Audio Research Group","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056412131","display_name":"Kyogu Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Music and Audio Research Group, Seoul National University","Seoul National University,Music and Audio Research Group"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University,Music and Audio Research Group","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065510735"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.3048,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50775371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7224","last_page":"7228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9987999796867371,"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":0.9619121551513672},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.9276078343391418},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.657752513885498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6214563250541687},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5919538140296936},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5895384550094604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5386075973510742},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.526911199092865},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.49076470732688904},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.44652795791625977},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4291672110557556},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3175831437110901},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2609654664993286},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.21256881952285767},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.20538678765296936},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.13710057735443115},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.10719260573387146},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.07737463712692261},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05332496762275696}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9619121551513672},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9276078343391418},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.657752513885498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6214563250541687},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5919538140296936},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5895384550094604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5386075973510742},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.526911199092865},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.49076470732688904},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.44652795791625977},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4291672110557556},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3175831437110901},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2609654664993286},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.21256881952285767},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.20538678765296936},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.13710057735443115},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.10719260573387146},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.07737463712692261},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05332496762275696},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.13069","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.13069","pdf_url":"https://arxiv.org/pdf/1910.13069","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2982290989","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1910.13069","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1910.13069","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.13069","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/fj6f-xx28","is_oa":true,"landing_page_url":"https://doi.org/10.17023/fj6f-xx28","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.13069","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.13069","pdf_url":"https://arxiv.org/pdf/1910.13069","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982290989.pdf","grobid_xml":"https://content.openalex.org/works/W2982290989.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W1990079834","https://openalex.org/W2053883410","https://openalex.org/W2066598518","https://openalex.org/W2126552603","https://openalex.org/W2767052532","https://openalex.org/W2778460379","https://openalex.org/W2892620417","https://openalex.org/W2949382160","https://openalex.org/W2963568710","https://openalex.org/W2964243274","https://openalex.org/W2973046048","https://openalex.org/W2984106626","https://openalex.org/W6601203246","https://openalex.org/W6630833833","https://openalex.org/W6631229253","https://openalex.org/W6678318511","https://openalex.org/W6755135894"],"related_works":["https://openalex.org/W3016250102","https://openalex.org/W2102528110","https://openalex.org/W2111037747","https://openalex.org/W2849790107","https://openalex.org/W1557619878","https://openalex.org/W2220230773","https://openalex.org/W3006571012","https://openalex.org/W3087356222","https://openalex.org/W2559391159","https://openalex.org/W2814372287","https://openalex.org/W2354065972","https://openalex.org/W3168613051","https://openalex.org/W1578046625","https://openalex.org/W2154613350","https://openalex.org/W2138455584","https://openalex.org/W2031631009","https://openalex.org/W2248312987","https://openalex.org/W2964706117","https://openalex.org/W2061804607","https://openalex.org/W100127983"],"abstract_inverted_index":{"In":[0],"this":[1,33],"study,":[2],"we":[3,35,49,65,91,130],"define":[4],"the":[5,8,45,59,72,88,95,112,120,128],"identity":[6,53,60,69],"of":[7,61,100,106,122],"singer":[9,52,68],"with":[10,87],"two":[11,73],"independent":[12,74],"concepts":[13],"\u2013":[14,19],"timbre":[15,78,113],"and":[16,20,79,114],"singing":[17,24,80,104,115,124,141],"style":[18],"propose":[21],"a":[22,41,51,62,84,102,138],"multi-singer":[23,42],"synthesis":[25],"system":[26],"that":[27,55,76,94,132],"can":[28,56,136],"model":[29,39,43,77],"them":[30],"separately.":[31],"To":[32],"end,":[34],"extend":[36],"our":[37,133],"single-singer":[38],"into":[40],"in":[44],"following":[46],"ways:":[47],"first,":[48],"design":[50],"encoder":[54],"adequately":[57],"reflect":[58],"singer.":[63],"Second,":[64],"use":[66],"encoded":[67],"to":[70],"condition":[71],"decoders":[75],"style,":[81],"respectively.":[82],"Through":[83],"user":[85],"study":[86],"listening":[89],"tests,":[90],"experimentally":[92],"verify":[93],"proposed":[96,134],"framework":[97],"is":[98],"capable":[99],"generating":[101],"natural":[103],"voice":[105],"high":[107],"quality":[108],"while":[109,126],"independently":[110],"controlling":[111],"style.":[116],"Also,":[117],"by":[118],"using":[119],"method":[121],"changing":[123],"styles":[125],"fixing":[127],"timbre,":[129],"suggest":[131],"network":[135],"produce":[137],"more":[139],"expressive":[140],"voice.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-07-28T00:00:00"}
