{"id":"https://openalex.org/W2160767268","doi":"https://doi.org/10.1109/tasl.2013.2266773","title":"Multi-Stage Non-Negative Matrix Factorization for Monaural Singing Voice Separation","display_name":"Multi-Stage Non-Negative Matrix Factorization for Monaural Singing Voice Separation","publication_year":2013,"publication_date":"2013-06-06","ids":{"openalex":"https://openalex.org/W2160767268","doi":"https://doi.org/10.1109/tasl.2013.2266773","mag":"2160767268"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2013.2266773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2266773","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100934338","display_name":"Bilei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bilei Zhu","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318193","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4486-8341"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007642188","display_name":"Ruijiang Li","orcid":"https://orcid.org/0000-0002-0232-5998"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruijiang Li","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":7.6185,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.97866087,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"21","issue":"10","first_page":"2096","last_page":"2107"},"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":0.9986000061035156,"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/monaural","display_name":"Monaural","score":0.781233012676239},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7740365266799927},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7407684922218323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.677762508392334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6572598218917847},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6364477872848511},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5580339431762695},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.48641490936279297},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4788610637187958},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.449089914560318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4157700538635254},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.28173741698265076},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18418285250663757},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07677268981933594}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.781233012676239},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7740365266799927},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7407684922218323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.677762508392334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6572598218917847},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6364477872848511},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5580339431762695},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.48641490936279297},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4788610637187958},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.449089914560318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4157700538635254},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.28173741698265076},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18418285250663757},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07677268981933594},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2013.2266773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2266773","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W141230911","https://openalex.org/W1482650115","https://openalex.org/W1555938837","https://openalex.org/W1561135842","https://openalex.org/W1604012244","https://openalex.org/W1902027874","https://openalex.org/W1964208564","https://openalex.org/W1981755271","https://openalex.org/W2002016907","https://openalex.org/W2020335482","https://openalex.org/W2022668263","https://openalex.org/W2035852710","https://openalex.org/W2039844283","https://openalex.org/W2046281481","https://openalex.org/W2057745663","https://openalex.org/W2099904336","https://openalex.org/W2104298926","https://openalex.org/W2116244429","https://openalex.org/W2124539664","https://openalex.org/W2127851351","https://openalex.org/W2130768851","https://openalex.org/W2130770109","https://openalex.org/W2132597408","https://openalex.org/W2150415460","https://openalex.org/W2151785180","https://openalex.org/W2152591660","https://openalex.org/W2164098335","https://openalex.org/W2164282073","https://openalex.org/W2296573765","https://openalex.org/W2394506964","https://openalex.org/W2399506744","https://openalex.org/W2403272360","https://openalex.org/W4205778870","https://openalex.org/W4292023222","https://openalex.org/W6605679885","https://openalex.org/W6633219022","https://openalex.org/W6633727632","https://openalex.org/W6636121673","https://openalex.org/W6676113301","https://openalex.org/W6697668227","https://openalex.org/W6712043840","https://openalex.org/W6712781682","https://openalex.org/W6713555227"],"related_works":["https://openalex.org/W2551137307","https://openalex.org/W2100772705","https://openalex.org/W2113526703","https://openalex.org/W2123043102","https://openalex.org/W2577807713","https://openalex.org/W2396837968","https://openalex.org/W3094316140","https://openalex.org/W2547262076","https://openalex.org/W3133205200","https://openalex.org/W2098101267"],"abstract_inverted_index":{"Separating":[0],"singing":[1,34,136],"voice":[2,35],"from":[3,83,106,126],"music":[4,25,121],"accompaniment":[5,122],"can":[6],"be":[7],"of":[8,45,119,145,154],"interest":[9],"for":[10,33,73,95],"many":[11],"applications":[12],"such":[13],"as":[14],"melody":[15],"extraction,":[16],"singer":[17],"identification,":[18],"lyrics":[19],"alignment":[20],"and":[21,23,62,87,116,150,167],"recognition,":[22],"content-based":[24],"retrieval.":[26],"In":[27],"this":[28],"paper,":[29],"a":[30,88],"novel":[31],"algorithm":[32,43,163],"separation":[36],"in":[37],"monaural":[38],"mixtures":[39],"is":[40,53,71,93,164],"proposed.":[41],"The":[42],"consists":[44],"two":[46],"stages,":[47],"where":[48],"non-negative":[49],"matrix":[50],"factorization":[51],"(NMF)":[52],"applied":[54],"to":[55,77,99],"decompose":[56],"the":[57,74,96,111,120,127,135,141,151,161],"mixture":[58],"spectrograms":[59],"with":[60,131],"long":[61],"short":[63,147],"windows":[64],"respectively.":[65],"A":[66],"spectral":[67],"discontinuity":[68,90],"thresholding":[69,91],"method":[70,92],"devised":[72],"long-window":[75],"NMF":[76,80,98,102],"select":[78],"out":[79,101,125],"components":[81,103],"originating":[82],"pitched":[84,115],"instrumental":[85],"sounds,":[86],"temporal":[89],"designed":[94],"short-window":[97],"pick":[100],"that":[104,160],"are":[105,123],"percussive":[107,117],"sounds.":[108],"By":[109],"eliminating":[110],"selected":[112],"components,":[113],"most":[114],"elements":[118],"filtered":[124],"input":[128],"sound":[129],"mixture,":[130],"little":[132],"effect":[133],"on":[134,140],"voice.":[137],"Extensive":[138],"testing":[139],"MIR-1K":[142],"public":[143],"dataset":[144,153],"1000":[146],"audio":[148],"clips":[149],"Beach-Boys":[152],"14":[155],"full-track":[156],"real-world":[157],"songs":[158],"showed":[159],"proposed":[162],"both":[165],"effective":[166],"efficient.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}