{"id":"https://openalex.org/W4225300878","doi":"https://doi.org/10.1109/icassp43922.2022.9747536","title":"Few-Shot Musical Source Separation","display_name":"Few-Shot Musical Source Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225300878","doi":"https://doi.org/10.1109/icassp43922.2022.9747536"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747536","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100445125","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-9500-081X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Wang","raw_affiliation_strings":["New York University,Music and Audio Research Laboratory,NY,USA","Music and Audio Research Laboratory, New York University, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Laboratory,NY,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063832676","display_name":"Daniel Stoller","orcid":"https://orcid.org/0000-0002-8615-4144"},"institutions":[{"id":"https://openalex.org/I4210134791","display_name":"Saint Vladimir's Orthodox Theological Seminary","ror":"https://ror.org/0428qkc73","country_code":"US","type":"education","lineage":["https://openalex.org/I4210134791"]},{"id":"https://openalex.org/I4210122154","display_name":"Photon Spot (United States)","ror":"https://ror.org/01yxc0v75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122154"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Stoller","raw_affiliation_strings":["Spotify,New York,NY,USA","Spotify, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Spotify,New York,NY,USA","institution_ids":["https://openalex.org/I4210134791"]},{"raw_affiliation_string":"Spotify, New York, NY, USA","institution_ids":["https://openalex.org/I4210122154"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019790225","display_name":"Rachel Bittner","orcid":"https://orcid.org/0000-0001-7757-2232"},"institutions":[{"id":"https://openalex.org/I4210134791","display_name":"Saint Vladimir's Orthodox Theological Seminary","ror":"https://ror.org/0428qkc73","country_code":"US","type":"education","lineage":["https://openalex.org/I4210134791"]},{"id":"https://openalex.org/I4210122154","display_name":"Photon Spot (United States)","ror":"https://ror.org/01yxc0v75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122154"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rachel M. Bittner","raw_affiliation_strings":["Spotify,New York,NY,USA","Spotify, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Spotify,New York,NY,USA","institution_ids":["https://openalex.org/I4210134791"]},{"raw_affiliation_string":"Spotify, New York, NY, USA","institution_ids":["https://openalex.org/I4210122154"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pablo Bello","raw_affiliation_strings":["New York University,Music and Audio Research Laboratory,NY,USA","Music and Audio Research Laboratory, New York University, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Laboratory,NY,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100445125"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":1.7183,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87077409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"125"},"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":0.9973999857902527,"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":0.7225229740142822},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6464508771896362},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6401036977767944},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5698640942573547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5172541737556458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5058002471923828},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5052919983863831},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.4965055584907532},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4630700647830963},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.433843731880188},{"id":"https://openalex.org/keywords/conditioning","display_name":"Conditioning","score":0.4221707582473755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32080593705177307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08664864301681519},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08584430813789368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225229740142822},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6464508771896362},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6401036977767944},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5698640942573547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5172541737556458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058002471923828},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5052919983863831},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.4965055584907532},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4630700647830963},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.433843731880188},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.4221707582473755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32080593705177307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08664864301681519},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08584430813789368},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747536","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":35,"referenced_works":["https://openalex.org/W2098950531","https://openalex.org/W2127851351","https://openalex.org/W2296724634","https://openalex.org/W2552071709","https://openalex.org/W2669032454","https://openalex.org/W2760103357","https://openalex.org/W2774707525","https://openalex.org/W2889404825","https://openalex.org/W2898963093","https://openalex.org/W2903502793","https://openalex.org/W2949756029","https://openalex.org/W2954304925","https://openalex.org/W2962753171","https://openalex.org/W2963452667","https://openalex.org/W2963751183","https://openalex.org/W2969034647","https://openalex.org/W2985214749","https://openalex.org/W2991107219","https://openalex.org/W2998490864","https://openalex.org/W3015753416","https://openalex.org/W3037149862","https://openalex.org/W3106104628","https://openalex.org/W3160972914","https://openalex.org/W3161651274","https://openalex.org/W3162801840","https://openalex.org/W3174280965","https://openalex.org/W4298310324","https://openalex.org/W6697040288","https://openalex.org/W6746914816","https://openalex.org/W6751512325","https://openalex.org/W6757632829","https://openalex.org/W6766320909","https://openalex.org/W6766938422","https://openalex.org/W6786608192","https://openalex.org/W6786621524"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W4214877189","https://openalex.org/W2074502265","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2334685461","https://openalex.org/W2108473831"],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"approaches":[2],"to":[3,10,24,65,74,126],"musical":[4,35,90],"source":[5,36,44],"separation":[6,37,45],"are":[7,17],"often":[8],"limited":[9],"the":[11,15,52,63,67,76,85,93,107,121],"instrument":[12],"classes":[13],"that":[14,100],"models":[16,87],"trained":[18,86],"on":[19,88],"and":[20,95,116],"do":[21],"not":[22],"generalize":[23],"separate":[25],"unseen":[26,117],"instruments.":[27,118],"To":[28,119],"address":[29],"this,":[30],"we":[31,133],"propose":[32],"a":[33,41,57,71,127],"few-shot":[34,58,103],"paradigm.":[38],"We":[39,55,83,98],"condition":[40],"generic":[42],"U-Net":[43,64,77],"model":[46,112],"using":[47],"few":[48],"audio":[49,68],"examples":[50,69,142],"of":[51,123,130],"target":[53],"instrument.":[54],"train":[56],"conditioning":[59,72,104,138,151],"encoder":[60],"jointly":[61],"with":[62,136,146],"encode":[66],"into":[70],"vector":[73],"configure":[75],"via":[78],"feature-wise":[79],"linear":[80],"modulation":[81],"(FiLM).":[82],"evaluate":[84],"real":[89],"recordings":[91],"in":[92],"MUSDB18":[94],"MedleyDB":[96],"datasets.":[97],"show":[99],"our":[101,124],"proposed":[102],"paradigm":[105],"outperforms":[106],"base-line":[108],"one-hot":[109],"instrument-class":[110],"conditioned":[111],"for":[113],"both":[114],"seen":[115],"extend":[120],"scope":[122],"approach":[125],"wider":[128],"variety":[129],"real-world":[131],"scenarios,":[132],"also":[134],"experiment":[135],"different":[137,144],"example":[139],"characteristics,":[140],"including":[141],"from":[143],"recordings,":[145],"multiple":[147],"sources,":[148],"or":[149],"negative":[150],"examples.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}