{"id":"https://openalex.org/W2593552751","doi":"https://doi.org/10.1109/mwscas.2016.7870055","title":"Vocal separation using improved robust principal component analysis and post-processing","display_name":"Vocal separation using improved robust principal component analysis and post-processing","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2593552751","doi":"https://doi.org/10.1109/mwscas.2016.7870055","mag":"2593552751"},"language":"en","primary_location":{"id":"doi:10.1109/mwscas.2016.7870055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mwscas.2016.7870055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 59th International Midwest Symposium on Circuits and Systems (MWSCAS)","raw_type":"proceedings-article"},"type":"article","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/A5034851349","display_name":"Tomohiro Watanabe","orcid":"https://orcid.org/0000-0002-6175-8064"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomohiro Watanabe","raw_affiliation_strings":["EEE Dept., Keio Univ., Yokohama, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"EEE Dept., Keio Univ., Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052510171","display_name":"Takanori Fujisawa","orcid":"https://orcid.org/0000-0001-7632-5846"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Fujisawa","raw_affiliation_strings":["EEE Dept., Keio Univ., Yokohama, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"EEE Dept., Keio Univ., Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090181402","display_name":"Masaaki Ikehara","orcid":"https://orcid.org/0000-0003-3461-1507"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaaki Ikehara","raw_affiliation_strings":["EEE Dept., Keio Univ., Yokohama, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"EEE Dept., Keio Univ., Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034851349"],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":null,"apc_paid":null,"fwci":0.7565,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74449208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"abs 912 3599","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11447","display_name":"Blind Source Separation Techniques","score":0.9995999932289124,"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":0.9986000061035156,"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/robust-principal-component-analysis","display_name":"Robust principal component analysis","score":0.9344152808189392},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8422278165817261},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6984744668006897},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.59071946144104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5065330266952515},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4952146112918854},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.48994678258895874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44632479548454285},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43452104926109314},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.42656558752059937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41206175088882446},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.26919126510620117},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.16456258296966553}],"concepts":[{"id":"https://openalex.org/C2777749129","wikidata":"https://www.wikidata.org/wiki/Q17148469","display_name":"Robust principal component analysis","level":3,"score":0.9344152808189392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8422278165817261},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6984744668006897},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.59071946144104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5065330266952515},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4952146112918854},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.48994678258895874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44632479548454285},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43452104926109314},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.42656558752059937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41206175088882446},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.26919126510620117},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.16456258296966553},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mwscas.2016.7870055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mwscas.2016.7870055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 59th International Midwest Symposium on Circuits and Systems (MWSCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W125824305","https://openalex.org/W1604012244","https://openalex.org/W1964544556","https://openalex.org/W1970714145","https://openalex.org/W2022668263","https://openalex.org/W2023800933","https://openalex.org/W2030254567","https://openalex.org/W2101868363","https://openalex.org/W2127851351","https://openalex.org/W2153586312","https://openalex.org/W2164098335","https://openalex.org/W2951443864","https://openalex.org/W6605016247","https://openalex.org/W6636121673","https://openalex.org/W6640723650","https://openalex.org/W6682221641"],"related_works":["https://openalex.org/W2380927352","https://openalex.org/W3178621026","https://openalex.org/W2085553065","https://openalex.org/W2367227827","https://openalex.org/W2364535454","https://openalex.org/W2137598809","https://openalex.org/W127732203","https://openalex.org/W2593552751","https://openalex.org/W3203816112","https://openalex.org/W2284031406"],"abstract_inverted_index":{"Due":[0],"to":[1,17,75,115],"the":[2,5,10,90,96,104,108,125,131,139],"spread":[3],"of":[4,9,22,32,60,62,103,107],"Internet":[6],"and":[7,34,45,128],"improvement":[8],"audio":[11,23],"compression":[12],"technology,":[13],"we":[14,83,94,111,120],"need":[15],"technologies":[16],"handle":[18],"a":[19,63,85],"large":[20],"number":[21],"files.":[24],"Separating":[25],"singing":[26],"voice":[27],"from":[28],"music":[29],"is":[30,36],"one":[31],"them":[33],"it":[35],"used":[37],"in":[38,65,78],"many":[39],"applications,":[40],"such":[41],"as":[42],"lyric":[43],"retrieval":[44],"singer":[46],"recognition.":[47],"Recently,":[48],"robust":[49],"principal":[50],"component":[51],"analysis":[52],"(RPCA)":[53],"has":[54],"been":[55],"proposed,":[56],"which":[57],"makes":[58,101],"use":[59,102],"repetition":[61],"phrase":[64],"an":[66],"accompaniment.":[67],"We":[68],"assume":[69],"that":[70,100,130],"there":[71],"are":[72],"some":[73],"points":[74],"be":[76],"improved":[77],"RPCA.":[79],"In":[80],"this":[81],"paper,":[82],"propose":[84,95],"developed":[86],"method":[87],"based":[88],"on":[89],"RPCA":[91,98,141],"algorithm.":[92],"First,":[93],"extended":[97],"algorithm":[99,123,133],"two":[105],"features":[106],"spectrogram.":[109],"Second,":[110],"apply":[112],"simple":[113],"post-processing":[114],"remove":[116],"noise":[117],"effectively.":[118],"Lastly,":[119],"experiment":[121],"our":[122],"using":[124],"MIR-1K":[126],"dataset":[127],"confirm":[129],"proposed":[132],"shows":[134],"better":[135],"separation":[136],"performance":[137],"than":[138],"conventional":[140],"method.":[142]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}