{"id":"https://openalex.org/W2552071709","doi":"https://doi.org/10.1109/icassp.2017.7952118","title":"Deep clustering and conventional networks for music separation: Stronger together","display_name":"Deep clustering and conventional networks for music separation: Stronger together","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2552071709","doi":"https://doi.org/10.1109/icassp.2017.7952118","mag":"2552071709","pmid":"https://pubmed.ncbi.nlm.nih.gov/29398973"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1611.06265","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620750","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0003-0661-3628"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":178,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2017","issue":null,"first_page":"61","last_page":"65"},"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":0.9998000264167786,"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":0.9987000226974487,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8613095283508301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7476201057434082},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6674157381057739},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.64317387342453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6146673560142517},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.586093544960022},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5299968123435974},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5096004009246826},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.4685405492782593},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46176663041114807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.421791136264801},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38804471492767334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2949799597263336},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.0774998664855957}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8613095283508301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476201057434082},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6674157381057739},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.64317387342453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6146673560142517},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.586093544960022},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5299968123435974},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5096004009246826},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4685405492782593},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46176663041114807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.421791136264801},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38804471492767334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2949799597263336},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0774998664855957},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2017.7952118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmid:29398973","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29398973","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)","raw_type":null},{"id":"pmh:oai:arXiv.org:1611.06265","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1611.06265","pdf_url":"https://arxiv.org/pdf/1611.06265","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"},{"id":"pmh:oai:pubmedcentral.nih.gov:5791533","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5791533","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1611.06265","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1611.06265","pdf_url":"https://arxiv.org/pdf/1611.06265","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"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G123412604","display_name":null,"funder_award_id":"R01 DC014279","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1563939609","https://openalex.org/W1570504315","https://openalex.org/W1964208564","https://openalex.org/W2046869671","https://openalex.org/W2124539664","https://openalex.org/W2164098335","https://openalex.org/W2166209411","https://openalex.org/W2221409856","https://openalex.org/W2243290847","https://openalex.org/W2296073425","https://openalex.org/W2318192700","https://openalex.org/W2375367034","https://openalex.org/W2399506744","https://openalex.org/W2401638432","https://openalex.org/W2405258286","https://openalex.org/W2516392987","https://openalex.org/W2560977758","https://openalex.org/W2962715207","https://openalex.org/W2962949994","https://openalex.org/W6634309418","https://openalex.org/W6712781682","https://openalex.org/W6712931226","https://openalex.org/W6713676406","https://openalex.org/W6730178624"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2539388437","https://openalex.org/W2107688514","https://openalex.org/W2137288760"],"abstract_inverted_index":{"Deep":[0],"clustering":[1,59,71,82,126],"is":[2,34],"the":[3,16,55,72,75,103,122,151],"first":[4],"method":[5],"to":[6,49,147],"handle":[7],"general":[8],"audio":[9],"separation":[10,30,90],"scenarios":[11],"with":[12],"multiple":[13],"sources":[14,69],"of":[15,23,105,124,156],"same":[17],"type":[18],"and":[19,67,95,127],"an":[20,61,144],"arbitrary":[21],"number":[22],"sources,":[24],"performing":[25],"impressively":[26],"in":[27,39,74,92,137],"speaker-independent":[28],"speech":[29],"tasks.":[31],"However,":[32],"little":[33],"known":[35],"about":[36],"its":[37,114,157],"effectiveness":[38],"other":[40],"challenging":[41],"situations":[42],"such":[43],"as":[44],"music":[45],"source":[46,56],"separation.":[47],"Contrary":[48],"conventional":[50,84,100,128],"networks":[51,85,101],"that":[52,80],"directly":[53],"estimate":[54],"signals,":[57],"deep":[58,81,125],"generates":[60],"embedding":[62,76],"for":[63,108],"each":[64],"time-frequency":[65],"bin,":[66],"separates":[68],"by":[70],"bins":[73],"space.":[77],"We":[78],"show":[79],"outperforms":[83,154],"on":[86],"a":[87,138],"singing":[88],"voice":[89],"task,":[91],"both":[93],"matched":[94],"mismatched":[96],"conditions,":[97],"even":[98],"though":[99],"have":[102],"advantage":[104],"end-to-end":[106],"training":[107],"best":[109],"signal":[110],"approximation,":[111],"presumably":[112],"because":[113],"more":[115],"flexible":[116],"objective":[117],"engenders":[118],"better":[119],"regularization.":[120],"Since":[121],"strengths":[123],"network":[129,141],"architectures":[130],"appear":[131],"complementary,":[132],"we":[133],"explore":[134],"combining":[135],"them":[136],"single":[139],"hybrid":[140],"trained":[142],"via":[143],"approach":[145],"akin":[146],"multi-task":[148],"learning.":[149],"Remarkably,":[150],"combination":[152],"significantly":[153],"either":[155],"components.":[158]},"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":13},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":47},{"year":2019,"cited_by_count":38},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}