{"id":"https://openalex.org/W1526336542","doi":"https://doi.org/10.1109/icassp.2015.7178034","title":"Singing voice analysis and editing based on mutually dependent F0 estimation and source separation","display_name":"Singing voice analysis and editing based on mutually dependent F0 estimation and source separation","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1526336542","doi":"https://doi.org/10.1109/icassp.2015.7178034","mag":"1526336542"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5087321595","display_name":"Yukara Ikemiya","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukara Ikemiya","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan","[Graduate School of Informatics, Kyoto University, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Graduate School of Informatics, Kyoto University, Japan]","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan","[Graduate School of Informatics, Kyoto University, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Graduate School of Informatics, Kyoto University, Japan]","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsutoshi Itoyama","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan","[Graduate School of Informatics, Kyoto University, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Graduate School of Informatics, Kyoto University, Japan]","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"574","last_page":"578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9082119464874268},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7476921081542969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7342808842658997},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6834880113601685},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5583738088607788},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.55713951587677},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.541517972946167},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4493742287158966},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.42292681336402893},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.41603371500968933},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3511780798435211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34229153394699097},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3382854759693146},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10089674592018127}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9082119464874268},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7476921081542969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7342808842658997},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6834880113601685},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5583738088607788},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.55713951587677},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.541517972946167},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4493742287158966},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.42292681336402893},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.41603371500968933},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3511780798435211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34229153394699097},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3382854759693146},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10089674592018127},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.711.2416","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.2416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/%7Eyoshii/papers/icassp-2015-ikemiya.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5300062852","display_name":null,"funder_award_id":"24220006","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1519655822","https://openalex.org/W1555938837","https://openalex.org/W1592438470","https://openalex.org/W1736339626","https://openalex.org/W1964208564","https://openalex.org/W1974421892","https://openalex.org/W1976069042","https://openalex.org/W1979654135","https://openalex.org/W1991135550","https://openalex.org/W2022668263","https://openalex.org/W2023800933","https://openalex.org/W2036339641","https://openalex.org/W2048310341","https://openalex.org/W2098796164","https://openalex.org/W2100891835","https://openalex.org/W2100989275","https://openalex.org/W2108753079","https://openalex.org/W2116244429","https://openalex.org/W2124232593","https://openalex.org/W2125838338","https://openalex.org/W2127851351","https://openalex.org/W2130581557","https://openalex.org/W2130770109","https://openalex.org/W2134039779","https://openalex.org/W2134387846","https://openalex.org/W2161632835","https://openalex.org/W2164098335","https://openalex.org/W2172046423","https://openalex.org/W2293399065","https://openalex.org/W2399539226","https://openalex.org/W2403272360","https://openalex.org/W6631117800","https://openalex.org/W6633219022","https://openalex.org/W6635375625","https://openalex.org/W6674623533","https://openalex.org/W6678415575","https://openalex.org/W6696653561","https://openalex.org/W6712695463","https://openalex.org/W6713555227","https://openalex.org/W6913044885","https://openalex.org/W6968750206"],"related_works":["https://openalex.org/W2138997758","https://openalex.org/W2997975677","https://openalex.org/W1965243342","https://openalex.org/W2402362233","https://openalex.org/W2765931784","https://openalex.org/W3120099295","https://openalex.org/W2562176306","https://openalex.org/W2053207518","https://openalex.org/W3192255518","https://openalex.org/W1526336542"],"abstract_inverted_index":{"This":[0,167],"paper":[1],"presents":[2],"a":[3,45,57,159,177,184],"novel":[4],"framework":[5,113],"that":[6,60,209],"improves":[7],"both":[8,213],"vocal":[9,41,68,202,214],"fundamental":[10],"frequency":[11],"(F0)":[12],"estimation":[13,216],"and":[14,49,70,217],"singing":[15,34,53,86,133,151,172,218],"voice":[16,35,54,87,134,152,173,219],"separation":[17,36,174],"by":[18,55,135,153,175],"making":[19],"effective":[20],"use":[21],"of":[22,26,66,122],"the":[23,40,52,63,67,76,85,93,120,125,132,149,155,196],"mutual":[24,97],"dependency":[25,98],"those":[27,115],"two":[28,116],"tasks.":[29],"A":[30],"typical":[31],"approach":[32],"to":[33,38,80,170,199],"is":[37,78,145],"estimate":[39],"F0":[42,73,143,215],"contour":[43,144],"from":[44,92,148],"target":[46,94],"music":[47],"signal":[48],"then":[50,146],"extract":[51,131],"using":[56,119,136],"time-frequency":[58,178],"mask":[59,179,185],"passes":[61],"only":[62,84],"harmonic":[64,188],"components":[65],"F0s":[69,203],"overtones.":[71],"Vocal":[72],"estimation,":[74],"on":[75,103,163,181,187],"contrary,":[77],"considered":[79],"become":[81],"easier":[82],"if":[83],"can":[88],"be":[89],"extracted":[90],"accurately":[91],"signal.":[95],"Such":[96],"has":[99],"scarcely":[100],"been":[101],"focused":[102],"in":[104,124,204],"most":[105],"conventional":[106],"studies.":[107],"To":[108],"overcome":[109],"this":[110],"limitation,":[111],"our":[112],"alternates":[114],"tasks":[117],"while":[118],"results":[121,191],"each":[123],"other.":[126],"More":[127],"specifically,":[128],"we":[129,194],"first":[130],"robust":[137],"principal":[138],"component":[139],"analysis":[140],"(RPCA).":[141],"The":[142],"estimated":[147],"separated":[150],"finding":[154],"optimal":[156],"path":[157],"over":[158],"F0-saliency":[160],"spectrogram":[161],"based":[162,180,186],"subharmonic":[164],"summation":[165],"(SHS).":[166],"enables":[168],"us":[169],"improve":[171],"combining":[176],"RPCA":[182],"with":[183],"structures.":[189],"Experimental":[190],"obtained":[192],"when":[193],"used":[195],"proposed":[197],"technique":[198],"directly":[200],"edit":[201],"popular-music":[205],"audio":[206],"signals":[207],"showed":[208],"it":[210],"significantly":[211],"improved":[212],"separation.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}