{"id":"https://openalex.org/W4408354042","doi":"https://doi.org/10.1109/icassp49660.2025.10887744","title":"Subtractive Training for Music Stem Insertion Using Latent Diffusion Models","display_name":"Subtractive Training for Music Stem Insertion Using Latent Diffusion Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354042","doi":"https://doi.org/10.1109/icassp49660.2025.10887744"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887744","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":"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/A5099670544","display_name":"Ivan Villa-Renteria","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Villa-Renteria","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084824021","display_name":"Mason Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mason Long Wang","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109743072","display_name":"Zachary Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Shah","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101459221","display_name":"Zhe Li","orcid":"https://orcid.org/0000-0003-3510-0610"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhe Li","raw_affiliation_strings":["Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379496","display_name":"Soo-Hyun Kim","orcid":"https://orcid.org/0009-0000-3054-2394"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soohyun Kim","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108949299","display_name":"Neelesh Ramachandran","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neelesh Ramachandran","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001436196","display_name":"Mert Pilanc\u0131","orcid":"https://orcid.org/0000-0002-0870-9992"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mert Pilanci","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03960996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9927999973297119,"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":0.9927999973297119,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9383000135421753,"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"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9017999768257141,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.6409640312194824},{"id":"https://openalex.org/keywords/subtractive-color","display_name":"Subtractive color","score":0.5815778970718384},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4578569829463959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4095267951488495},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38404709100723267},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.10608625411987305},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07642275094985962},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07462432980537415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6409640312194824},{"id":"https://openalex.org/C150799807","wikidata":"https://www.wikidata.org/wiki/Q374081","display_name":"Subtractive color","level":2,"score":0.5815778970718384},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4578569829463959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4095267951488495},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38404709100723267},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.10608625411987305},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07642275094985962},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07462432980537415},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887744","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":[{"score":0.49000000953674316,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2295936755","https://openalex.org/W2526050071","https://openalex.org/W2948978827","https://openalex.org/W2971458685","https://openalex.org/W2992838650","https://openalex.org/W3094550259","https://openalex.org/W4296334467","https://openalex.org/W4312933868","https://openalex.org/W4386076215","https://openalex.org/W4392903114","https://openalex.org/W4401023606","https://openalex.org/W4401023775","https://openalex.org/W6678969435","https://openalex.org/W6766320909","https://openalex.org/W6776218486","https://openalex.org/W6778883912","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6799000596","https://openalex.org/W6840155194","https://openalex.org/W6841366371","https://openalex.org/W6842893850","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6849635556","https://openalex.org/W6850818779","https://openalex.org/W6853096648","https://openalex.org/W6854494257","https://openalex.org/W6855932524","https://openalex.org/W6857775612","https://openalex.org/W6868771744","https://openalex.org/W6869165705"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2064042445","https://openalex.org/W63093223","https://openalex.org/W1992507414","https://openalex.org/W3156046797","https://openalex.org/W1502270335","https://openalex.org/W2046641174","https://openalex.org/W2120307627"],"abstract_inverted_index":{"We":[0,54,96],"present":[1],"Subtractive":[2,81],"Training<sup":[3],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[4],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[5],"a":[6,25,33,39,57,128,132],"simple":[7],"and":[8,42,74,119,155],"novel":[9],"method":[10,23],"for":[11,158],"synthesizing":[12],"individual":[13],"musical":[14],"instrument":[15,66,87,130],"stems":[16,73,88],"given":[17],"other":[18],"instruments":[19,139],"as":[20],"context.":[21],"This":[22],"pairs":[24],"dataset":[26,37],"of":[27,35,110,116,127],"complete":[28],"music":[29],"mixes":[30],"with":[31,92],"1)":[32],"variant":[34],"the":[36,48,64,71,75,93,103,108,111,125,137,140],"lacking":[38],"specific":[40],"stem,":[41,67],"2)":[43],"LLM-generated":[44],"instructions":[45],"describing":[46],"how":[47],"missing":[49,65],"stem":[50,113],"should":[51],"be":[52],"reintroduced.":[53],"then":[55],"fine-tune":[56],"pre-trained":[58],"text-to-audio":[59],"diffusion":[60],"model":[61],"to":[62,106,123,147],"generate":[63],"guided":[68],"by":[69],"both":[70],"existing":[72,94],"text":[76,104],"instruction.":[77],"Our":[78],"results":[79],"demonstrate":[80],"Training\u2019s":[82],"efficacy":[83],"in":[84,114,131],"creating":[85],"authentic":[86],"that":[89,99],"seamlessly":[90],"blend":[91],"tracks.":[95],"also":[97],"show":[98],"we":[100,143],"can":[101],"use":[102],"instruction":[105],"control":[107],"generation":[109],"inserted":[112],"terms":[115],"rhythm,":[117],"dynamics,":[118],"genre,":[120],"allowing":[121],"us":[122],"modify":[124],"style":[126],"single":[129],"full":[133],"song":[134],"while":[135],"keeping":[136],"remaining":[138],"same.":[141],"Lastly,":[142],"extend":[144],"this":[145],"technique":[146],"MIDI":[148],"formats,":[149],"successfully":[150],"generating":[151],"compatible":[152],"bass,":[153],"drum,":[154],"guitar":[156],"parts":[157],"incomplete":[159],"arrangements.":[160]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}