{"id":"https://openalex.org/W4385569670","doi":"https://doi.org/10.1109/taslp.2023.3302237","title":"Unsupervised Deep Unfolded Representation Learning for Singing Voice Separation","display_name":"Unsupervised Deep Unfolded Representation Learning for Singing Voice Separation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385569670","doi":"https://doi.org/10.1109/taslp.2023.3302237"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3302237","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2023.3302237","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/A5058549121","display_name":"Weitao Yuan","orcid":"https://orcid.org/0000-0003-1900-8259"},"institutions":[{"id":"https://openalex.org/I198091727","display_name":"Tiangong University","ror":"https://ror.org/00xsr9m91","country_code":"CN","type":"education","lineage":["https://openalex.org/I198091727"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weitao Yuan","raw_affiliation_strings":["Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems, School of Software, Tiangong University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1900-8259","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems, School of Software, Tiangong University, Tianjin, China","institution_ids":["https://openalex.org/I198091727"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035486167","display_name":"Shengbei Wang","orcid":"https://orcid.org/0000-0002-4713-5012"},"institutions":[{"id":"https://openalex.org/I198091727","display_name":"Tiangong University","ror":"https://ror.org/00xsr9m91","country_code":"CN","type":"education","lineage":["https://openalex.org/I198091727"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbei Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems, School of Software, Tiangong University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-4713-5012","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems, School of Software, Tiangong University, Tianjin, China","institution_ids":["https://openalex.org/I198091727"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048371289","display_name":"Jianming Wang","orcid":"https://orcid.org/0000-0003-2685-4437"},"institutions":[{"id":"https://openalex.org/I198091727","display_name":"Tiangong University","ror":"https://ror.org/00xsr9m91","country_code":"CN","type":"education","lineage":["https://openalex.org/I198091727"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianming Wang","raw_affiliation_strings":["Centre for Engineering Faculty, Tiangong University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-2685-4437","affiliations":[{"raw_affiliation_string":"Centre for Engineering Faculty, Tiangong University, Tianjin, China","institution_ids":["https://openalex.org/I198091727"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6605-2052","affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8393-5703","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08434587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"3206","last_page":"3220"},"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":0.9988999962806702,"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/prior-probability","display_name":"Prior probability","score":0.7802202701568604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6772685050964355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5904826521873474},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5474255681037903},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.526390790939331},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5235214233398438},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4479691684246063},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44346413016319275},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.43590646982192993},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42305320501327515},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4209449887275696},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32163935899734497}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7802202701568604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6772685050964355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5904826521873474},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5474255681037903},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.526390790939331},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5235214233398438},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4479691684246063},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44346413016319275},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.43590646982192993},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42305320501327515},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4209449887275696},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32163935899734497},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3302237","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2023.3302237","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":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G268415559","display_name":null,"funder_award_id":"ZR2020QF007","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G4280680737","display_name":null,"funder_award_id":"62201314","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6948971276","display_name":null,"funder_award_id":"62072335","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7732325329","display_name":null,"funder_award_id":"62176182","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"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W228380312","https://openalex.org/W658020064","https://openalex.org/W1964208564","https://openalex.org/W1964544556","https://openalex.org/W2095980290","https://openalex.org/W2123708030","https://openalex.org/W2133478409","https://openalex.org/W2150415460","https://openalex.org/W2158131535","https://openalex.org/W2160767268","https://openalex.org/W2163922914","https://openalex.org/W2164098335","https://openalex.org/W2164931791","https://openalex.org/W2519994964","https://openalex.org/W2528314500","https://openalex.org/W2744110160","https://openalex.org/W2767358676","https://openalex.org/W2796571515","https://openalex.org/W2803968356","https://openalex.org/W2913783817","https://openalex.org/W2950621961","https://openalex.org/W2963191020","https://openalex.org/W2964005873","https://openalex.org/W2964058413","https://openalex.org/W2972411915","https://openalex.org/W2981436548","https://openalex.org/W2985707019","https://openalex.org/W2990594533","https://openalex.org/W2997574889","https://openalex.org/W2998657200","https://openalex.org/W3015700067","https://openalex.org/W3015753416","https://openalex.org/W3035664806","https://openalex.org/W3037149862","https://openalex.org/W3040688604","https://openalex.org/W3045150439","https://openalex.org/W3092379909","https://openalex.org/W3102246635","https://openalex.org/W3112170415","https://openalex.org/W3113680622","https://openalex.org/W3123649567","https://openalex.org/W3127032689","https://openalex.org/W3133902371","https://openalex.org/W3160733670","https://openalex.org/W3165462110","https://openalex.org/W3174257816","https://openalex.org/W4205247735","https://openalex.org/W4206471589","https://openalex.org/W4221151515","https://openalex.org/W4229650096","https://openalex.org/W4287753648","https://openalex.org/W4298310324","https://openalex.org/W4322615131","https://openalex.org/W4372260250","https://openalex.org/W4385245566","https://openalex.org/W6621906925","https://openalex.org/W6626481562","https://openalex.org/W6681096077","https://openalex.org/W6682962330","https://openalex.org/W6724411756","https://openalex.org/W6727623532","https://openalex.org/W6739901393","https://openalex.org/W6745397693","https://openalex.org/W6751707404","https://openalex.org/W6766320909","https://openalex.org/W6780053291","https://openalex.org/W6780322082","https://openalex.org/W6784335252","https://openalex.org/W6790082833","https://openalex.org/W6796386619"],"related_works":["https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3174759195","https://openalex.org/W3167013339","https://openalex.org/W4287121366","https://openalex.org/W60493759","https://openalex.org/W4308619659","https://openalex.org/W3213069564","https://openalex.org/W4378421684","https://openalex.org/W4294203825"],"abstract_inverted_index":{"Learning":[0],"effective":[1,34],"vocal":[2],"representations":[3],"from":[4],"a":[5,9,89,133],"waveform":[6],"mixture":[7],"is":[8,202],"crucial":[10],"but":[11],"challenging":[12],"task":[13],"for":[14,39,70,94],"deep":[15,61,72],"neural":[16,31],"network":[17],"(DNN)-based":[18],"singing":[19],"voice":[20],"separation":[21],"(SVS).":[22],"Successful":[23],"representation":[24,74],"learning":[25,75],"(RL)":[26],"depends":[27],"heavily":[28],"on":[29,46],"well-designed":[30],"architectures":[32,48],"and":[33,65,77,103,111,149,157,182,190,208],"general":[35,50,99],"priors.":[36],"However,":[37],"DNNs":[38],"RL":[40,64,87],"in":[41,117,147,185],"SVS":[42,189],"are":[43,107],"mostly":[44],"built":[45],"generic":[47],"without":[49],"priors":[51,170],"being":[52],"systematically":[53],"considered.":[54],"To":[55],"address":[56,143],"these":[57,180],"issues,":[58],"we":[59,85,113],"introduce":[60],"unfolding":[62],"to":[63,163,171],"propose":[66],"two":[67],"RL-based":[68],"models":[69],"SVS,":[71],"unfolded":[73],"(DURL)":[76],"optimal":[78],"transport":[79],"DURL":[80,110,122,148,181,206],"(OT-DURL).":[81],"In":[82,109],"both":[83,210],"models,":[84],"formulate":[86],"as":[88,127,138],"sequence":[90],"of":[91,175,221],"optimization":[92,145],"problems":[93,146],"signal":[95],"reconstruction,":[96],"where":[97],"three":[98],"priors,":[100],"synthesis,":[101],"non-negative,":[102],"our":[104],"novel":[105,164],"analysis,":[106],"incorporated.":[108],"OT-DURL,":[112],"take":[114],"different":[115,172],"approaches":[116],"penalizing":[118],"the":[119,124,139,144,152,159,168,176,186,199,205,215,222],"analysis":[120],"prior.":[121],"uses":[123,132],"Euclidean":[125],"distance":[126],"its":[128],"penalty,":[129],"while":[130],"OT-DURL":[131,150,183,200],"more":[134],"sophisticated":[135],"penalty":[136],"known":[137],"OT":[140],"distance.":[141],"We":[142,178],"with":[151,219],"first-order":[153],"operator":[154],"splitting":[155],"algorithm":[156],"unfold":[158],"obtained":[160],"iterative":[161],"algorithms":[162],"encoders,":[165],"by":[166],"mapping":[167],"synthesis/analysis/non-negative":[169],"interpretable":[173],"sublayers":[174],"encoders.":[177],"evaluated":[179],"encoders":[184,211],"unsupervised":[187],"informed":[188],"supervised":[191],"Open-Unmix":[192],"frameworks.":[193],"Experimental":[194],"results":[195],"indicate":[196],"that":[197],"(1)":[198],"encoder":[201,207],"better":[203],"than":[204],"(2)":[209],"can":[212],"considerably":[213],"improve":[214],"vocal-signal-separation":[216],"performance":[217],"compared":[218],"those":[220],"baseline":[223],"model.":[224]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}