{"id":"https://openalex.org/W4392903036","doi":"https://doi.org/10.1109/icassp48485.2024.10447981","title":"Midi-Voice: Expressive Zero-Shot Singing Voice Synthesis via Midi-Driven Priors","display_name":"Midi-Voice: Expressive Zero-Shot Singing Voice Synthesis via Midi-Driven Priors","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903036","doi":"https://doi.org/10.1109/icassp48485.2024.10447981"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":"https://openalex.org/A5114136996","display_name":"Dong-Min Byun","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Min Byun","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320186","display_name":"Sang-Hoon Lee","orcid":"https://orcid.org/0009-0000-9828-1063"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Hoon Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101212448","display_name":"Ji-Sang Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ji-Sang Hwang","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2013Whan Lee","orcid":"https://orcid.org/0000-0002-6249-4996"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":3.9293,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94467737,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12622","last_page":"12626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/midi","display_name":"MIDI","score":0.9745191931724548},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9169759750366211},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7027608156204224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6778808236122131},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.48111361265182495},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4100250005722046},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23299729824066162},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11559084057807922}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.9745191931724548},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9169759750366211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027608156204224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6778808236122131},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48111361265182495},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4100250005722046},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23299729824066162},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11559084057807922},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1478288009","display_name":null,"funder_award_id":"2021-0-02068","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2804209865","display_name":null,"funder_award_id":"2019\u20130\u201300079","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2953128317","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G4643994530","display_name":null,"funder_award_id":"2021-0-02068","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8436554242","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"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":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1966527337","https://openalex.org/W2946200149","https://openalex.org/W2963925437","https://openalex.org/W2972910332","https://openalex.org/W2973046048","https://openalex.org/W2992988687","https://openalex.org/W2997520586","https://openalex.org/W3000389243","https://openalex.org/W3015844196","https://openalex.org/W3026874504","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3110257065","https://openalex.org/W3158762648","https://openalex.org/W3174285493","https://openalex.org/W3196760057","https://openalex.org/W3207340675","https://openalex.org/W4224920322","https://openalex.org/W4281736089","https://openalex.org/W4286899907","https://openalex.org/W4307323391","https://openalex.org/W4366460484","https://openalex.org/W4385571362","https://openalex.org/W4402905495","https://openalex.org/W6763832098","https://openalex.org/W6771763809","https://openalex.org/W6777694618","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6795261426","https://openalex.org/W6795807602","https://openalex.org/W6802838302","https://openalex.org/W6838843145","https://openalex.org/W6851724922","https://openalex.org/W6853570719"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4242364395","https://openalex.org/W2386555541","https://openalex.org/W3042962886","https://openalex.org/W2920621887","https://openalex.org/W2187442448","https://openalex.org/W889314198","https://openalex.org/W4285031015","https://openalex.org/W2580099843"],"abstract_inverted_index":{"Recently,":[0],"singing":[1,32,46,52,68,95,111,115,140,148],"voice":[2,47,53,69,96,112,149],"synthesis":[3,48],"(SVS)":[4],"models":[5,16,135],"have":[6],"shown":[7],"significant":[8],"progress":[9],"with":[10],"generative":[11],"models.":[12],"However,":[13],"previous":[14,134],"SVS":[15],"inaccurately":[17],"predict":[18],"prior":[19,60,77,105],"and":[20,49,82,113,142],"fundamental":[21],"frequency":[22],"(F0)":[23],"for":[24,44,66,106,114],"unseen":[25],"speakers,":[26],"resulting":[27,92],"in":[28,38,93,136,146],"a":[29,58,62,75,102,108],"low-quality":[30],"generated":[31],"voice.":[33],"To":[34],"address":[35],"these":[36],"issues,":[37],"this":[39,83],"paper,":[40],"we":[41],"propose":[42,101],"MIDI-Voice":[43,131],"expressive":[45,110,139],"robust":[50],"zero-shot":[51,147],"style":[54,70,97,116,150],"transfer.":[55],"We":[56,72,99],"employ":[57],"MIDI-based":[59],"to":[61],"score-based":[63],"diffusion":[64],"model":[65],"better":[67],"adaptation.":[71,98],"first":[73],"generate":[74],"MIDI-driven":[76],"from":[78,123],"the":[79,86,124,133,144],"musical":[80],"score,":[81],"only":[84],"includes":[85],"note":[87],"information,":[88],"not":[89],"speaker":[90],"information":[91,122],"high-quality":[94],"also":[100,143],"DDSP-based":[103],"MIDI-style":[104],"synthesizing":[107,137],"more":[109],"adaptation,":[117],"although":[118],"it":[119],"requires":[120],"additional":[121],"audio.":[125],"The":[126],"experimental":[127],"results":[128],"show":[129],"that":[130],"outperforms":[132],"an":[138],"voice,":[141],"superiority":[145],"transfer":[151],"performance.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
