{"id":"https://openalex.org/W4408352240","doi":"https://doi.org/10.1109/icassp49660.2025.10889421","title":"Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models","display_name":"Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352240","doi":"https://doi.org/10.1109/icassp49660.2025.10889421"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5094208255","display_name":"Tornike Karchkhadze","orcid":"https://orcid.org/0009-0008-9799-8191"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tornike Karchkhadze","raw_affiliation_strings":["University of California San Diego,San Diego,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego,San Diego,USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033902274","display_name":"Mohammad Izadi","orcid":"https://orcid.org/0000-0003-3561-3942"},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Rasool Izadi","raw_affiliation_strings":["Bose Corp.,Framingham,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corp.,Framingham,USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042278809","display_name":"Shlomo Dubnov","orcid":"https://orcid.org/0000-0003-0222-1125"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Dubnov","raw_affiliation_strings":["University of California San Diego,San Diego,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego,San Diego,USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9775000214576721,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/separation","display_name":"Separation (statistics)","score":0.6446037888526917},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.6145071983337402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5997985601425171},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5300944447517395},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.45401421189308167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3251844048500061},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1735154092311859},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.04830119013786316}],"concepts":[{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6446037888526917},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.6145071983337402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5997985601425171},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5300944447517395},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.45401421189308167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3251844048500061},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1735154092311859},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.04830119013786316},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":53,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2519091744","https://openalex.org/W2760103357","https://openalex.org/W2952218014","https://openalex.org/W2963751183","https://openalex.org/W2963816101","https://openalex.org/W2965481235","https://openalex.org/W2972478942","https://openalex.org/W2972653970","https://openalex.org/W2990594533","https://openalex.org/W2998490864","https://openalex.org/W2998657200","https://openalex.org/W3095999710","https://openalex.org/W3162801840","https://openalex.org/W3213726885","https://openalex.org/W4224297089","https://openalex.org/W4225261970","https://openalex.org/W4225293699","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4320712896","https://openalex.org/W4372269936","https://openalex.org/W4372341629","https://openalex.org/W4392903114","https://openalex.org/W4392904237","https://openalex.org/W4392908898","https://openalex.org/W4401043564","https://openalex.org/W4402671601","https://openalex.org/W4409365005","https://openalex.org/W4412172710","https://openalex.org/W6640963894","https://openalex.org/W6679045638","https://openalex.org/W6732429163","https://openalex.org/W6755257315","https://openalex.org/W6774212381","https://openalex.org/W6776218486","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6784499681","https://openalex.org/W6795742094","https://openalex.org/W6840561836","https://openalex.org/W6840815571","https://openalex.org/W6848578254","https://openalex.org/W6848854281","https://openalex.org/W6849002408","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6853096648","https://openalex.org/W6854990061","https://openalex.org/W6869810883","https://openalex.org/W6892454952"],"related_works":["https://openalex.org/W2789518417","https://openalex.org/W4213217485","https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W2566545183","https://openalex.org/W2499449816","https://openalex.org/W2059085722","https://openalex.org/W4210856988","https://openalex.org/W238145802","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"have":[2],"recently":[3],"shown":[4],"strong":[5],"potential":[6],"in":[7,17],"both":[8,33,63],"music":[9,12,68],"generation":[10,59,87,111,128],"and":[11,39,66,112,115,126],"source":[13,64,123],"separation":[14,65,113],"tasks.":[15,129],"Although":[16],"early":[18],"stages,":[19],"a":[20,29,55,79],"trend":[21],"is":[22],"emerging":[23],"towards":[24],"integrating":[25],"these":[26],"tasks":[27],"into":[28],"single":[30],"framework,":[31],"as":[32,43],"involve":[34],"generating":[35],"musically":[36],"aligned":[37],"parts":[38],"can":[40],"be":[41],"seen":[42],"facets":[44],"of":[45,62,76,92],"the":[46,72,95,102],"same":[47],"generative":[48],"process.":[49],"In":[50],"this":[51],"work,":[52],"we":[53],"introduce":[54],"latent":[56],"diffusion-based":[57],"multi-track":[58,67],"model":[60,83,100],"capable":[61],"synthesis":[69],"by":[70,88],"learning":[71],"joint":[73],"probability":[74],"distribution":[75],"tracks":[77,93],"sharing":[78],"musical":[80],"context.":[81],"Our":[82],"also":[84],"enables":[85],"arrangement":[86,127],"creating":[89],"any":[90],"subset":[91],"given":[94],"others.":[96],"We":[97],"trained":[98],"our":[99],"on":[101],"Slakh2100":[103],"dataset,":[104],"compared":[105],"it":[106],"with":[107],"an":[108],"existing":[109],"simultaneous":[110],"model,":[114],"observed":[116],"significant":[117],"improvements":[118],"across":[119],"objective":[120],"metrics":[121],"for":[122],"separation,":[124],"music,":[125],"Sound":[130],"examples":[131],"are":[132],"available":[133],"at":[134],"https://msg-ld.github.io/.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
