{"id":"https://openalex.org/W1964544556","doi":"https://doi.org/10.1109/taslp.2015.2396681","title":"Separation of Singing Voice Using Nonnegative Matrix Partial Co-Factorization for Singer Identification","display_name":"Separation of Singing Voice Using Nonnegative Matrix Partial Co-Factorization for Singer Identification","publication_year":2015,"publication_date":"2015-01-26","ids":{"openalex":"https://openalex.org/W1964544556","doi":"https://doi.org/10.1109/taslp.2015.2396681","mag":"1964544556"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2396681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2396681","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":null,"license_id":null,"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":["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/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Hu","raw_affiliation_strings":["School of Electronic and Information Engineering, Xian Jiaotong University, Xian, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Xian Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071277762","display_name":"Guizhong Liu","orcid":"https://orcid.org/0000-0001-9149-4576"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guizhong Liu","raw_affiliation_strings":["School of Electronic and Information Engineering, Xian Jiaotong University, Xian, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Xian Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042363663"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":3.7333,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93842925,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"23","issue":"4","first_page":"643","last_page":"653"},"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":0.9993000030517578,"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":0.9988999962806702,"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":0.9420359134674072},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.676571249961853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5052583813667297},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.4219295382499695},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.41273033618927},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.22452202439308167},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08304840326309204}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9420359134674072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.676571249961853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5052583813667297},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4219295382499695},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.41273033618927},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.22452202439308167},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08304840326309204},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2396681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2396681","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4838091533","display_name":null,"funder_award_id":"No.61173110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W168903045","https://openalex.org/W1491186237","https://openalex.org/W1570824959","https://openalex.org/W1588437207","https://openalex.org/W1964208564","https://openalex.org/W2000211333","https://openalex.org/W2000911789","https://openalex.org/W2027804983","https://openalex.org/W2041732360","https://openalex.org/W2041823554","https://openalex.org/W2050688514","https://openalex.org/W2061140267","https://openalex.org/W2066768226","https://openalex.org/W2074354966","https://openalex.org/W2083667973","https://openalex.org/W2096482524","https://openalex.org/W2122982914","https://openalex.org/W2123708030","https://openalex.org/W2124539664","https://openalex.org/W2130768851","https://openalex.org/W2130855892","https://openalex.org/W2132597408","https://openalex.org/W2133525256","https://openalex.org/W2134039779","https://openalex.org/W2143855671","https://openalex.org/W2145905122","https://openalex.org/W2149425615","https://openalex.org/W2150415460","https://openalex.org/W2152591660","https://openalex.org/W2158074454","https://openalex.org/W2164098335","https://openalex.org/W2169698188","https://openalex.org/W2295824433","https://openalex.org/W2403272360","https://openalex.org/W2561557072","https://openalex.org/W3152035499","https://openalex.org/W3209383001","https://openalex.org/W3216401400","https://openalex.org/W4233392025","https://openalex.org/W6629509115","https://openalex.org/W6635159179","https://openalex.org/W6679357244","https://openalex.org/W6697408287","https://openalex.org/W6713555227","https://openalex.org/W6803793192"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795"],"abstract_inverted_index":{"In":[0,67],"order":[1],"to":[2,13,55],"improve":[3,168],"the":[4,34,57,68,73,79,82,92,104,118,126,156,162,173,181,187,197],"performance":[5],"of":[6,26,49,84,95,129,159,184],"singer":[7,185],"identification,":[8,186],"we":[9],"propose":[10],"a":[11,42,102,136,143],"system":[12,24],"separate":[14,56],"singing":[15,50,61,75,85,96,130,149,163,174,188,199],"voice":[16,51,62,76,86,97,131,164,175,189],"from":[17,155],"music":[18],"accompaniment":[19,54,65],"for":[20,180],"monaural":[21],"recordings.":[22],"Our":[23],"consists":[25],"two":[27],"key":[28],"stages.":[29],"The":[30],"first":[31,80,88],"stage":[32],"exploits":[33],"nonnegative":[35],"matrix":[36,44],"partial":[37],"co-factorization":[38],"(NMPCF),":[39],"which":[40],"is":[41,120,193],"joint":[43],"decomposition":[45],"integrating":[46],"prior":[47],"knowledge":[48],"and":[52,64,90],"pure":[53],"mixture":[58],"signal":[59,145],"into":[60],"portion":[63],"portion.":[66],"second":[69],"stage,":[70,81],"based":[71],"on":[72],"separated":[74,190],"obtained":[77],"by":[78,135,191],"pitches":[83],"are":[87,108],"estimated":[89],"then":[91],"harmonic":[93,106,124],"components":[94,107,115],"can":[98,132,166],"be":[99,133],"distinguished.":[100],"For":[101],"frame,":[103],"distinguished":[105],"regarded":[109],"as":[110],"reliable":[111],"while":[112,179],"other":[113],"frequency":[114],"unreliable,":[116],"thus":[117],"spectrum":[119,140],"incomplete.":[121],"With":[122],"those":[123],"components,":[125],"complete":[127],"spectrums":[128],"reconstructed":[134],"missing":[137],"feature":[138],"method,":[139],"reconstruction,":[141],"obtaining":[142],"refined":[144,198],"with":[146,172],"more":[147,194],"clean":[148],"voice.":[150,200],"Experimental":[151],"results":[152],"demonstrate":[153],"that,":[154],"point":[157,182],"view":[158,183],"source":[160],"separation,":[161],"refinement":[165],"further":[167],"\u0394SNR":[169],"in":[170],"contrast":[171],"separation":[176],"using":[177],"NMPCF,":[178],"NMPCF":[192],"appropriate":[195],"than":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}