{"id":"https://openalex.org/W4323064860","doi":"https://doi.org/10.1109/taslp.2023.3252272","title":"Unsupervised Music Source Separation Using Differentiable Parametric Source Models","display_name":"Unsupervised Music Source Separation Using Differentiable Parametric Source Models","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323064860","doi":"https://doi.org/10.1109/taslp.2023.3252272"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3252272","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3252272","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10058592.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10058592.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042191000","display_name":"Kilian Schulze-Forster","orcid":"https://orcid.org/0000-0001-8397-7914"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Kilian Schulze-Forster","raw_affiliation_strings":["LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0001-8397-7914","affiliations":[{"raw_affiliation_string":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Richard","raw_affiliation_strings":["LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0002-4960-0010","affiliations":[{"raw_affiliation_string":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110881904","display_name":"Liam Kelley","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Liam Kelley","raw_affiliation_strings":["LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066312580","display_name":"Clement S. J. Doire","orcid":"https://orcid.org/0000-0002-8739-4510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clement S. J. Doire","raw_affiliation_strings":["Sonos Inc., Paris, France"],"raw_orcid":"https://orcid.org/0000-0002-8739-4510","affiliations":[{"raw_affiliation_string":"Sonos Inc., Paris, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028865449","display_name":"Roland Badeau","orcid":"https://orcid.org/0000-0002-9630-6877"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Roland Badeau","raw_affiliation_strings":["LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0002-9630-6877","affiliations":[{"raw_affiliation_string":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8668,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96226294,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"1276","last_page":"1289"},"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":0.9994999766349792,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7565306425094604},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7546099424362183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6472331285476685},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5555918216705322},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5004377365112305},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4682641625404358},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4511120915412903},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.44203802943229675},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4407598078250885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43377697467803955},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.27216869592666626},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1280132532119751}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565306425094604},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7546099424362183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6472331285476685},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5555918216705322},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5004377365112305},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4682641625404358},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4511120915412903},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.44203802943229675},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4407598078250885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43377697467803955},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.27216869592666626},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1280132532119751},{"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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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":2,"locations":[{"id":"doi:10.1109/taslp.2023.3252272","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3252272","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10058592.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04038023v1","is_oa":true,"landing_page_url":"https://telecom-paris.hal.science/hal-04038023","pdf_url":"https://telecom-paris.hal.science/hal-04038023/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2023, 31, pp.1276-1289. ⟨10.1109/TASLP.2023.3252272⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3252272","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3252272","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10058592.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4326088756","display_name":null,"funder_award_id":"101052978","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4924294516","display_name":"New Frontiers in Music Information Processing","funder_award_id":"765068","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6592793251","display_name":null,"funder_award_id":"ERC, HI-Audio, 101052978","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4323064860.pdf","grobid_xml":"https://content.openalex.org/works/W4323064860.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W1500684166","https://openalex.org/W1519698338","https://openalex.org/W1587896874","https://openalex.org/W1604034532","https://openalex.org/W1605424093","https://openalex.org/W1902027874","https://openalex.org/W1963637322","https://openalex.org/W2009674825","https://openalex.org/W2022194925","https://openalex.org/W2025112803","https://openalex.org/W2032026410","https://openalex.org/W2088432713","https://openalex.org/W2089959702","https://openalex.org/W2098101267","https://openalex.org/W2104770568","https://openalex.org/W2108494558","https://openalex.org/W2116244429","https://openalex.org/W2150415460","https://openalex.org/W2221409856","https://openalex.org/W2326591006","https://openalex.org/W2340199271","https://openalex.org/W2460742184","https://openalex.org/W2500358397","https://openalex.org/W2734774145","https://openalex.org/W2899515918","https://openalex.org/W2901552243","https://openalex.org/W2903502793","https://openalex.org/W2918296821","https://openalex.org/W2933708090","https://openalex.org/W2962866891","https://openalex.org/W2963175743","https://openalex.org/W2963992487","https://openalex.org/W2964058413","https://openalex.org/W2964199361","https://openalex.org/W2971458685","https://openalex.org/W2972411915","https://openalex.org/W3037968286","https://openalex.org/W3041356940","https://openalex.org/W3090496396","https://openalex.org/W3090751054","https://openalex.org/W3095999710","https://openalex.org/W3104539075","https://openalex.org/W3133902371","https://openalex.org/W3160751854","https://openalex.org/W3168140565","https://openalex.org/W4206319965","https://openalex.org/W4236937599","https://openalex.org/W4251742697","https://openalex.org/W4298310324","https://openalex.org/W4312790010","https://openalex.org/W6628322026","https://openalex.org/W6631190155","https://openalex.org/W6634627538","https://openalex.org/W6676956424","https://openalex.org/W6713134421","https://openalex.org/W6744199053","https://openalex.org/W6759107158","https://openalex.org/W6766320909","https://openalex.org/W6770984470","https://openalex.org/W6771763809","https://openalex.org/W6780226713","https://openalex.org/W6780730805","https://openalex.org/W6781725382","https://openalex.org/W6782889728","https://openalex.org/W6783557883","https://openalex.org/W6784488536","https://openalex.org/W6784499681","https://openalex.org/W6788137280"],"related_works":["https://openalex.org/W2547262076","https://openalex.org/W1565566036","https://openalex.org/W2563421448","https://openalex.org/W2774154397","https://openalex.org/W2921513691","https://openalex.org/W2534043196","https://openalex.org/W2098101267","https://openalex.org/W1979654135","https://openalex.org/W2615370628","https://openalex.org/W2806198829"],"abstract_inverted_index":{"Supervised":[0],"deep":[1,49,129,171],"learning":[2,50,130,172],"approaches":[3],"to":[4,31,52,71,146],"underdetermined":[5],"audio":[6],"source":[7,23,54,57,85,102,139],"separation":[8,111,155,174],"achieve":[9],"state-of-the-art":[10],"performance":[11],"but":[12],"require":[13],"a":[14,38,45,61,77,108,127,142],"dataset":[15],"of":[16,79,138,165],"mixtures":[17],"along":[18],"with":[19,60,181],"their":[20,89],"corresponding":[21],"isolated":[22],"signals.":[24,103],"Such":[25],"datasets":[26],"can":[27],"be":[28],"extremely":[29],"costly":[30],"obtain":[32],"for":[33,40],"musical":[34,53],"mixtures.":[35],"This":[36,167],"raises":[37],"need":[39],"unsupervised":[41,47],"methods.":[42],"We":[43],"propose":[44],"novel":[46],"model-based":[48],"approach":[51,152],"separation.":[55],"Each":[56],"is":[58,69,184],"modelled":[59],"differentiable":[62],"parametric":[63],"source-filter":[64],"model.":[65],"A":[66],"neural":[67],"network":[68],"trained":[70,159],"reconstruct":[72],"the":[73,80,84,100,115,136,150],"observed":[74],"mixture":[75],"as":[76],"sum":[78],"sources":[81],"by":[82],"estimating":[83],"models'":[86],"parameters":[87],"given":[88],"fundamental":[90],"frequencies.":[91],"At":[92],"test":[93],"time,":[94],"soft":[95],"masks":[96],"are":[97],"obtained":[98],"from":[99],"synthesized":[101],"The":[104],"experimental":[105],"evaluation":[106],"on":[107,122,160],"vocal":[109],"ensemble":[110],"task":[112],"shows":[113],"that":[114],"proposed":[116,151],"method":[117,144],"outperforms":[118],"learning-free":[119],"methods":[120],"based":[121,173],"nonnegative":[123],"matrix":[124],"factorization":[125],"and":[126],"supervised":[128],"baseline.":[131],"Integrating":[132],"domain":[133],"knowledge":[134],"in":[135,176],"form":[137],"models":[140],"into":[141],"data-driven":[143],"leads":[145],"high":[147],"data":[148,180],"efficiency:":[149],"achieves":[153],"good":[154],"quality":[156],"even":[157],"when":[158],"less":[161],"than":[162],"three":[163],"minutes":[164],"audio.":[166],"work":[168],"makes":[169],"powerful":[170],"usable":[175],"scenarios":[177],"where":[178],"training":[179],"ground":[182],"truth":[183],"expensive":[185],"or":[186],"nonexistent.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}