{"id":"https://openalex.org/W4392902821","doi":"https://doi.org/10.1109/icassp48485.2024.10447244","title":"A Fully Differentiable Model for Unsupervised Singing Voice Separation","display_name":"A Fully Differentiable Model for Unsupervised Singing Voice Separation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902821","doi":"https://doi.org/10.1109/icassp48485.2024.10447244"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://telecom-paris.hal.science/hal-04356813/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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":["Institut Polytechnique de Paris,LTCI, Télécom Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093836253","display_name":"Pierre Chouteau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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":"Pierre Chouteau","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083296120","display_name":"Bernardo Torres","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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":"Bernardo Torres","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8554,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68504373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"946","last_page":"950"},"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":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.7384794354438782},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.729512095451355},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6833059787750244},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6001555919647217},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5688766241073608},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5600101351737976},{"id":"https://openalex.org/keywords/schulze-method","display_name":"Schulze method","score":0.47645190358161926},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4717199206352234},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.46273383498191833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44427207112312317},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38033631443977356},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2662646770477295},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1238914430141449},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.11267530918121338},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0809655487537384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384794354438782},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.729512095451355},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6833059787750244},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6001555919647217},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5688766241073608},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5600101351737976},{"id":"https://openalex.org/C178350558","wikidata":"https://www.wikidata.org/wiki/Q113","display_name":"Schulze method","level":2,"score":0.47645190358161926},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4717199206352234},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.46273383498191833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44427207112312317},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38033631443977356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2662646770477295},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1238914430141449},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.11267530918121338},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0809655487537384},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04356813v2","is_oa":true,"landing_page_url":"https://telecom-paris.hal.science/hal-04356813","pdf_url":"https://telecom-paris.hal.science/hal-04356813/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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea. ⟨10.1109/ICASSP48485.2024.10447244⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04356813v2","is_oa":true,"landing_page_url":"https://telecom-paris.hal.science/hal-04356813","pdf_url":"https://telecom-paris.hal.science/hal-04356813/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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea. ⟨10.1109/ICASSP48485.2024.10447244⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.44999998807907104,"display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G4326088756","display_name":"Hybrid and Interpretable Deep neural audio machines","funder_award_id":"101052978","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":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392902821.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W1902027874","https://openalex.org/W2108494558","https://openalex.org/W2116244429","https://openalex.org/W2168103573","https://openalex.org/W2752796333","https://openalex.org/W2903502793","https://openalex.org/W2964058413","https://openalex.org/W2971458685","https://openalex.org/W2972411915","https://openalex.org/W3081424945","https://openalex.org/W3090496396","https://openalex.org/W3112170415","https://openalex.org/W4212774754","https://openalex.org/W4281560197","https://openalex.org/W4323064860","https://openalex.org/W6697195168","https://openalex.org/W6746836464","https://openalex.org/W6759107158","https://openalex.org/W6771763809","https://openalex.org/W6781725382","https://openalex.org/W6782889728","https://openalex.org/W6783557883","https://openalex.org/W6862931503"],"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":{"A":[0],"novel":[1,96],"model":[2,18,58,88],"was":[3],"recently":[4],"proposed":[5],"by":[6,89],"Schulze-Forster":[7],"et":[8],"al.":[9],"in":[10,119],"[1]":[11],"for":[12,37,123],"unsupervised":[13],"music":[14],"source":[15,29],"separation.":[16],"This":[17],"allows":[19],"to":[20,78,83],"tackle":[21],"some":[22],"of":[23,27,108,114],"the":[24,35,101,106],"major":[25],"shortcomings":[26],"existing":[28],"separation":[30],"frameworks.":[31],"Specifically,":[32],"it":[33],"eliminates":[34],"need":[36],"isolated":[38],"sources":[39,51],"during":[40],"training,":[41],"performs":[42],"efficiently":[43],"with":[44],"limited":[45],"data,":[46],"and":[47,65,82,94,116,126],"can":[48],"handle":[49],"homogeneous":[50],"(such":[52],"as":[53],"singing":[54],"voice).":[55],"But,":[56],"this":[57,74,80],"relies":[59],"on":[60],"an":[61,67],"external":[62],"multipitch":[63,92],"estimator":[64,93],"incorporates":[66],"Ad":[68],"hoc":[69],"voice":[70],"assignment":[71,98],"procedure.":[72],"In":[73],"paper,":[75],"we":[76,117],"propose":[77],"extend":[79],"framework":[81],"build":[84],"a":[85,91,95,112],"fully":[86],"differentiable":[87,97],"integrating":[90],"module":[99],"within":[100],"core":[102],"model.":[103],"We":[104],"show":[105],"merits":[107],"our":[109],"approach":[110],"through":[111],"set":[113],"experiments,":[115],"highlight":[118],"particular":[120],"its":[121],"potential":[122],"processing":[124],"diverse":[125],"unseen":[127],"data.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}