{"id":"https://openalex.org/W2318192700","doi":"https://doi.org/10.1109/taslp.2016.2577879","title":"Singing Voice Separation and Vocal F0 Estimation Based on Mutual Combination of Robust Principal Component Analysis and Subharmonic Summation","display_name":"Singing Voice Separation and Vocal F0 Estimation Based on Mutual Combination of Robust Principal Component Analysis and Subharmonic Summation","publication_year":2016,"publication_date":"2016-06-07","ids":{"openalex":"https://openalex.org/W2318192700","doi":"https://doi.org/10.1109/taslp.2016.2577879","mag":"2318192700"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2577879","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2577879","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2016.2577879","any_repository_has_fulltext":true},"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":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","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":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","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":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, 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":5.0015,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95947089,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":"11","first_page":"2084","last_page":"2095"},"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":0.9998999834060669,"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":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9189460873603821},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7299098372459412},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6837678551673889},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6396744847297668},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.6092880964279175},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.5421079993247986},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.4896688759326935},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4790114760398865},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34946247935295105},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34807533025741577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2992587685585022}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9189460873603821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7299098372459412},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6837678551673889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6396744847297668},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6092880964279175},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.5421079993247986},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.4896688759326935},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4790114760398865},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34946247935295105},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34807533025741577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2992587685585022},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2016.2577879","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2577879","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1604.00192","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1604.00192","pdf_url":"https://arxiv.org/pdf/1604.00192","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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/taslp.2016.2577879","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2577879","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G698350668","display_name":"Emergence of Musical Intelligence Based on Probabilistic Integration of Signal and Symbolic Processing","funder_award_id":"26700020","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":57,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1519655822","https://openalex.org/W1555938837","https://openalex.org/W1578924114","https://openalex.org/W1580780811","https://openalex.org/W1592438470","https://openalex.org/W1736339626","https://openalex.org/W1964208564","https://openalex.org/W1974421892","https://openalex.org/W1976069042","https://openalex.org/W1976314171","https://openalex.org/W1988844105","https://openalex.org/W2000853276","https://openalex.org/W2022668263","https://openalex.org/W2023800933","https://openalex.org/W2036339641","https://openalex.org/W2037487247","https://openalex.org/W2048310341","https://openalex.org/W2062710265","https://openalex.org/W2098166503","https://openalex.org/W2098796164","https://openalex.org/W2100989275","https://openalex.org/W2107328928","https://openalex.org/W2116244429","https://openalex.org/W2124232593","https://openalex.org/W2127851351","https://openalex.org/W2130581557","https://openalex.org/W2130770109","https://openalex.org/W2131062138","https://openalex.org/W2134039779","https://openalex.org/W2134387846","https://openalex.org/W2152591660","https://openalex.org/W2160767268","https://openalex.org/W2161632835","https://openalex.org/W2164098335","https://openalex.org/W2169327228","https://openalex.org/W2172046423","https://openalex.org/W2207196656","https://openalex.org/W2293399065","https://openalex.org/W2296573765","https://openalex.org/W2296724634","https://openalex.org/W2401638432","https://openalex.org/W2402362233","https://openalex.org/W2403272360","https://openalex.org/W2405258286","https://openalex.org/W6631117800","https://openalex.org/W6633219022","https://openalex.org/W6635375625","https://openalex.org/W6678415575","https://openalex.org/W6696653561","https://openalex.org/W6697040288","https://openalex.org/W6697668227","https://openalex.org/W6712931226","https://openalex.org/W6713402318","https://openalex.org/W6713555227","https://openalex.org/W6713676406","https://openalex.org/W6929385289"],"related_works":["https://openalex.org/W2373880408","https://openalex.org/W405661683","https://openalex.org/W2532856746","https://openalex.org/W238390473","https://openalex.org/W2119168266","https://openalex.org/W4230480656","https://openalex.org/W2978145617","https://openalex.org/W2108382268","https://openalex.org/W2097873655","https://openalex.org/W2023774214"],"abstract_inverted_index":{"This":[0,51],"paper":[1],"presents":[2],"a":[3,37,88,130],"new":[4],"method":[5,74,156,172],"of":[6,60,62,69,96,146,161,179],"singing":[7,13,31,48,85,106,121,163,180],"voice":[8,14,49,164,181],"analysis":[9,80,188],"that":[10,56,140,153],"performs":[11,76],"mutually-dependent":[12],"separation":[15,165,182],"and":[16,41,166],"vocal":[17,42,167],"fundamental":[18],"frequency":[19],"(F0)":[20],"estimation.":[21,169],"Vocal":[22],"F0":[23,43,94,116,168],"estimation":[24],"is":[25,100],"considered":[26],"to":[27,184],"become":[28],"easier":[29],"if":[30],"voices":[32,86,107,122],"can":[33],"be":[34],"separated":[35,105,124],"from":[36,87,103],"music":[38,90,187],"audio":[39,91],"signal,":[40],"contours":[44],"are":[45,123],"useful":[46],"for":[47,53,82],"separation.":[50],"calls":[52],"an":[54,115,185],"approach":[55],"improves":[57],"the":[58,67,70,97,104,110,120,143,147,154,159,176],"performance":[59],"each":[61],"these":[63],"tasks":[64],"by":[65,108,128,135],"using":[66],"results":[68,151],"other.":[71],"The":[72,93,170],"proposed":[73,155,171],"first":[75],"robust":[77],"principal":[78],"component":[79],"(RPCA)":[81],"roughly":[83],"extracting":[84],"target":[89],"signal.":[92],"contour":[95],"main":[98],"melody":[99],"then":[101],"estimated":[102,148],"finding":[109],"optimal":[111],"temporal":[112],"path":[113],"over":[114],"saliency":[117],"spectrogram.":[118],"Finally,":[119],"again":[125],"more":[126],"accurately":[127],"combining":[129],"conventional":[131],"time-frequency":[132],"mask":[133,139],"given":[134],"RPCA":[136],"with":[137],"another":[138],"passes":[141],"only":[142],"harmonic":[144],"structures":[145],"F0s.":[149],"Experimental":[150],"showed":[152],"significantly":[157],"improved":[158],"performances":[160],"both":[162],"also":[173],"outperformed":[174],"all":[175],"other":[177],"methods":[178],"submitted":[183],"international":[186],"competition":[189],"called":[190],"MIREX":[191],"2014.":[192]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}