{"id":"https://openalex.org/W4385478423","doi":"https://doi.org/10.1109/icasspw59220.2023.10193575","title":"Pa\u15e7-HuBERT: Self-Supervised Music Source Separation Via Primitive Auditory Clustering And Hidden-Unit Bert","display_name":"Pa\u15e7-HuBERT: Self-Supervised Music Source Separation Via Primitive Auditory Clustering And Hidden-Unit Bert","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385478423","doi":"https://doi.org/10.1109/icasspw59220.2023.10193575"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5100451980","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-8357-3741"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"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":"Ke Chen","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","University of California San Diego (UCSD), La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"University of California San Diego (UCSD), La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"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":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102812631","display_name":"Fran\u00e7ois G. Germain","orcid":"https://orcid.org/0000-0002-8973-5315"},"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":"Fran\u00e7ois G. Germain","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064097430","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-0158-2837"},"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,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1848,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41717222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/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":0.9955000281333923,"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":0.8071445226669312},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7393430471420288},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7280900478363037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5467386245727539},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5323206782341003},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.4981539249420166},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48086291551589966},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4424936771392822},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4264027774333954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3760910630226135},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3391888439655304},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.15697422623634338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071445226669312},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7393430471420288},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7280900478363037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5467386245727539},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5323206782341003},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4981539249420166},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48086291551589966},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4424936771392822},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4264027774333954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3760910630226135},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3391888439655304},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.15697422623634338},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1976069042","https://openalex.org/W2018735295","https://openalex.org/W2022668263","https://openalex.org/W2100772705","https://openalex.org/W2296573765","https://openalex.org/W2407513162","https://openalex.org/W2580221632","https://openalex.org/W2622263826","https://openalex.org/W2773594497","https://openalex.org/W2896457183","https://openalex.org/W2902541609","https://openalex.org/W2916985722","https://openalex.org/W2962935966","https://openalex.org/W2963452667","https://openalex.org/W2972411915","https://openalex.org/W2973049979","https://openalex.org/W2982471419","https://openalex.org/W2990594533","https://openalex.org/W2995181338","https://openalex.org/W3037149862","https://openalex.org/W3043992176","https://openalex.org/W3090496396","https://openalex.org/W3138202130","https://openalex.org/W3138296617","https://openalex.org/W3160719641","https://openalex.org/W3198270377","https://openalex.org/W3199957557","https://openalex.org/W3205091761","https://openalex.org/W3206996142","https://openalex.org/W3207924272","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3216004336","https://openalex.org/W4221150524","https://openalex.org/W4226442948","https://openalex.org/W4284898017","https://openalex.org/W4285483774","https://openalex.org/W4286980120","https://openalex.org/W4296069264","https://openalex.org/W4298310324","https://openalex.org/W4312048190","https://openalex.org/W4312095873","https://openalex.org/W4319862462","https://openalex.org/W4372260250","https://openalex.org/W4375928773","https://openalex.org/W4385245566","https://openalex.org/W6656179950","https://openalex.org/W6657159850","https://openalex.org/W6674917984","https://openalex.org/W6697668227","https://openalex.org/W6732646663","https://openalex.org/W6739622702","https://openalex.org/W6739901393","https://openalex.org/W6751512325","https://openalex.org/W6755207826","https://openalex.org/W6756526489","https://openalex.org/W6766320909","https://openalex.org/W6780730805","https://openalex.org/W6783557883","https://openalex.org/W6801426729","https://openalex.org/W6804608017","https://openalex.org/W6809947431","https://openalex.org/W6840200333","https://openalex.org/W6845155585","https://openalex.org/W6846880785","https://openalex.org/W6846884369","https://openalex.org/W6848208918"],"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":{"In":[0,44],"spite":[1],"of":[2,13,70,80,116,168,182],"the":[3,10,59,67,71,83,124,129,145,150,180],"progress":[4],"in":[5,28,102],"music":[6,42,54,117,188],"source":[7,16,55,109,185,189],"separation":[8,37,56,88],"research,":[9],"small":[11,166],"amount":[12],"publicly-available":[14],"clean":[15,184],"data":[17,186],"remains":[18],"a":[19,32,49,94,105],"constant":[20],"limiting":[21],"factor":[22],"for":[23,35,53,108,187],"performance.":[24],"Thus,":[25],"recent":[26],"advances":[27],"self-supervised":[29,50,96,125],"learning":[30,51],"present":[31],"largely-unexplored":[33],"opportunity":[34],"improving":[36],"models":[38],"by":[39,58,75],"leveraging":[40],"unlabelled":[41],"data.":[43,170],"this":[45],"paper,":[46],"we":[47,99],"propose":[48,92],"framework":[52,137,174],"inspired":[57],"HuBERT":[60,73],"speech":[61],"representation":[62],"model.":[63],"We":[64,90,157],"first":[65],"investigate":[66],"potential":[68],"impact":[69],"original":[72,151],"model":[74],"inserting":[76],"an":[77,176],"adapted":[78],"version":[79],"it":[81,161],"into":[82],"well-known":[84],"Demucs":[85,152],"V2":[86,153],"time-domain":[87],"architecture.":[89],"then":[91],"Pa\u15e7-HuBERT,":[93],"time-frequency-domain":[95],"model,":[97],"that":[98,160],"later":[100],"use":[101],"combination":[103],"with":[104,165],"ResU-Net":[106],"decoder":[107],"separation.":[110,190],"Pa\u15e7-HuBERT":[111],"uses":[112],"primitive":[113],"auditory":[114],"features":[115],"as":[118],"unsupervised":[119],"clustering":[120],"labels":[121],"to":[122,179],"initialize":[123],"pretraining":[126],"process":[127],"using":[128],"Free":[130],"Music":[131],"Archive":[132],"(FMA)":[133],"dataset.":[134],"The":[135],"resulting":[136],"achieves":[138],"better":[139],"source-to-distortion":[140],"ratio":[141],"(SDR)":[142],"performance":[143,164],"on":[144],"MusDB18":[146],"test":[147],"set":[148],"than":[149],"and":[154],"Res-U-Net":[155],"models.":[156],"further":[158],"demonstrate":[159],"can":[162],"boost":[163],"amounts":[167],"supervised":[169],"Ultimately,":[171],"our":[172],"proposed":[173],"is":[175],"effective":[177],"solution":[178],"challenge":[181],"limited":[183]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}