{"id":"https://openalex.org/W2164098335","doi":"https://doi.org/10.1109/icassp.2012.6287816","title":"Singing-voice separation from monaural recordings using robust principal component analysis","display_name":"Singing-voice separation from monaural recordings using robust principal component analysis","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2164098335","doi":"https://doi.org/10.1109/icassp.2012.6287816","mag":"2164098335"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5076474156","display_name":"Po-Sen Huang","orcid":"https://orcid.org/0000-0003-1470-0991"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Sen Huang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034753989","display_name":"Scott Deeann Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Deeann Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.5487,"has_fulltext":false,"cited_by_count":337,"citation_normalized_percentile":{"value":0.99683804,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"60"},"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":0.9980000257492065,"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":0.8693588972091675},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8599789142608643},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.7719266414642334},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.703628420829773},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6982263326644897},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5212905406951904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.515796422958374},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.47357162833213806},{"id":"https://openalex.org/keywords/robust-principal-component-analysis","display_name":"Robust principal component analysis","score":0.45220068097114563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44512176513671875},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.42214053869247437},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4207392930984497},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16745850443840027},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.0810786783695221}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8693588972091675},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8599789142608643},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.7719266414642334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.703628420829773},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6982263326644897},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5212905406951904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.515796422958374},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.47357162833213806},{"id":"https://openalex.org/C2777749129","wikidata":"https://www.wikidata.org/wiki/Q17148469","display_name":"Robust principal component analysis","level":3,"score":0.45220068097114563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44512176513671875},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.42214053869247437},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4207392930984497},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16745850443840027},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0810786783695221},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","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":3,"locations":[{"id":"doi:10.1109/icassp.2012.6287816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.6722","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.6722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/speech/pubs/2012/huang12icassp2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.719.1467","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.719.1467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://minjekim.com/papers/ismir2014_phuang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W218087806","https://openalex.org/W1570504315","https://openalex.org/W1604012244","https://openalex.org/W1736339626","https://openalex.org/W1964208564","https://openalex.org/W2099904336","https://openalex.org/W2124539664","https://openalex.org/W2127851351","https://openalex.org/W2145962650","https://openalex.org/W2159898352","https://openalex.org/W2164282073","https://openalex.org/W2166209411","https://openalex.org/W2394506964","https://openalex.org/W6608768994","https://openalex.org/W6634309418","https://openalex.org/W6636121673","https://openalex.org/W6712043840"],"related_works":["https://openalex.org/W1976239252","https://openalex.org/W1614994442","https://openalex.org/W2035580387","https://openalex.org/W2103031592","https://openalex.org/W2003355886","https://openalex.org/W1967226023","https://openalex.org/W178436704","https://openalex.org/W3150394233","https://openalex.org/W3024900874","https://openalex.org/W2339586654"],"abstract_inverted_index":{"Separating":[0],"singing":[1,42],"voices":[2,43],"from":[3,69],"music":[4,15,70],"accompaniment":[5,23],"is":[6],"an":[7],"important":[8],"task":[9],"in":[10,29],"many":[11],"applications,":[12],"such":[13],"as":[14,47],"information":[16],"retrieval,":[17],"lyric":[18],"recognition":[19],"and":[20],"alignment.":[21],"Music":[22],"can":[24,44,94],"be":[25,28,45],"assumed":[26],"to":[27],"a":[30,80],"low-rank":[31],"subspace,":[32],"because":[33],"of":[34],"its":[35],"repetition":[36],"structure;":[37],"on":[38,56,86],"the":[39,75,87],"other":[40],"hand,":[41],"regarded":[46],"relatively":[48],"sparse":[49],"within":[50],"songs.":[51],"In":[52],"this":[53,57,92],"paper,":[54],"based":[55],"assumption,":[58],"we":[59,73],"propose":[60],"using":[61,79,107],"robust":[62],"principal":[63],"component":[64],"analysis":[65],"for":[66],"singing-voice":[67],"separation":[68,76],"accompaniment.":[71],"Moreover,":[72],"examine":[74],"result":[77],"by":[78],"binary":[81],"time-frequency":[82],"masking":[83],"method.":[84],"Evaluations":[85],"MIR-1K":[88],"dataset":[89],"show":[90],"that":[91],"method":[93],"achieve":[95],"around":[96],"1~1.4":[97],"dB":[98],"higher":[99],"GNSDR":[100],"compared":[101],"with":[102],"two":[103],"state-of-the-art":[104],"approaches":[105],"without":[106],"prior":[108],"training":[109],"or":[110],"requiring":[111],"particular":[112],"features.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":41},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":44},{"year":2017,"cited_by_count":32},{"year":2016,"cited_by_count":31},{"year":2015,"cited_by_count":40},{"year":2014,"cited_by_count":27},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}