{"id":"https://openalex.org/W4415036284","doi":"https://doi.org/10.21437/interspeech.2025-1397","title":"VibE-SVC: Vibrato Extraction with High-frequency F0 Contour for Singing Voice Conversion","display_name":"VibE-SVC: Vibrato Extraction with High-frequency F0 Contour for Singing Voice Conversion","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415036284","doi":"https://doi.org/10.21437/interspeech.2025-1397"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1397","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.20794","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Joon-Seung Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joon-Seung Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114136996","display_name":"Dong-Min Byun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong-Min Byun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033088100","display_name":"Hyung-Seok Oh","orcid":"https://orcid.org/0000-0001-7229-8123"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyung-Seok Oh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2013Whan Lee","orcid":"https://orcid.org/0000-0002-6249-4996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","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":1.2896,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81011738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1233","last_page":"1237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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":0.9940000176429749,"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":0.9887999892234802,"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/vibrato","display_name":"Vibrato","score":0.9966999888420105},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9205999970436096},{"id":"https://openalex.org/keywords/musical-tone","display_name":"Musical tone","score":0.641700029373169},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.42080000042915344},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41929998993873596},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4066999852657318},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.36059999465942383}],"concepts":[{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.9966999888420105},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9205999970436096},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6985999941825867},{"id":"https://openalex.org/C86011254","wikidata":"https://www.wikidata.org/wiki/Q2717062","display_name":"Musical tone","level":4,"score":0.641700029373169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.574400007724762},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1397","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.20794","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20794","pdf_url":"https://arxiv.org/pdf/2505.20794","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,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.20794","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20794","pdf_url":"https://arxiv.org/pdf/2505.20794","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,"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":[],"awards":[{"id":"https://openalex.org/G1277256358","display_name":null,"funder_award_id":"RS-2021-II212068","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G1451011034","display_name":null,"funder_award_id":"2021-II212068","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G490925689","display_name":null,"funder_award_id":"RS\u20102021\u2010II212068","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7699972493","display_name":null,"funder_award_id":"RS-2021-II212068","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8446819742","display_name":null,"funder_award_id":"RS-2024-00336673","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8458676037","display_name":null,"funder_award_id":"RS-2019-II190079","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G960095468","display_name":null,"funder_award_id":"RS-2019-II190079","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415036284.pdf","grobid_xml":"https://content.openalex.org/works/W4415036284.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Controlling":[0],"singing":[1,11,46,57,104],"style":[2,16],"is":[3],"crucial":[4],"for":[5,94],"achieving":[6],"an":[7],"expressive":[8],"and":[9,26,64,112],"natural":[10],"voice.":[12],"Among":[13],"the":[14,81],"various":[15],"factors,":[17],"vibrato":[18,32,66,76,92],"plays":[19],"a":[20,55],"key":[21],"role":[22],"in":[23,45],"conveying":[24],"emotions":[25],"enhancing":[27],"musical":[28],"depth.":[29],"However,":[30],"modeling":[31],"remains":[33],"challenging":[34],"due":[35],"to":[36,43],"its":[37],"dynamic":[38],"nature,":[39],"making":[40],"it":[41],"difficult":[42],"control":[44,93],"voice":[47,58],"conversion.":[48,117],"To":[49],"address":[50],"this,":[51],"we":[52],"propose":[53],"VibESVC,":[54],"controllable":[56],"conversion":[59],"model":[60,75],"that":[61,74,100],"explicitly":[62],"extracts":[63],"manipulates":[65],"using":[67],"discrete":[68],"wavelet":[69],"transform.":[70],"Unlike":[71],"previous":[72],"methods":[73],"implicitly,":[77],"our":[78],"approach":[79],"decomposes":[80],"F0":[82],"contour":[83],"into":[84],"frequency":[85],"components,":[86],"enabling":[87],"precise":[88],"transfer.":[89],"This":[90],"allows":[91],"enhanced":[95],"flexibility.":[96],"Experimental":[97],"results":[98],"show":[99],"VibE-SVC":[101],"effectively":[102],"transforms":[103],"styles":[105],"while":[106],"preserving":[107],"speaker":[108],"similarity.":[109],"Both":[110],"subjective":[111],"objective":[113],"evaluations":[114],"confirm":[115],"high-quality":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}
