{"id":"https://openalex.org/W4399197752","doi":"https://doi.org/10.48550/arxiv.2405.18386","title":"Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning","display_name":"Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning","publication_year":2024,"publication_date":"2024-05-28","ids":{"openalex":"https://openalex.org/W4399197752","doi":"https://doi.org/10.48550/arxiv.2405.18386"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.18386","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.18386","pdf_url":"https://arxiv.org/pdf/2405.18386","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.18386","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100635278","display_name":"Yixiao Zhang","orcid":"https://orcid.org/0000-0001-7026-4202"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Yixiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087321595","display_name":"Yukara Ikemiya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ikemiya, Yukara","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027289427","display_name":"Woosung Choi","orcid":"https://orcid.org/0000-0002-7001-3099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Woosung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031225419","display_name":"Naoki Murata","orcid":"https://orcid.org/0000-0001-7418-5173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murata, Naoki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017282176","display_name":"Marco A. Mart\u00ednez-Ram\u00edrez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mart\u00ednez-Ram\u00edrez, Marco A.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383258","display_name":"Liwei Lin","orcid":"https://orcid.org/0000-0001-7083-624X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Liwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027959958","display_name":"Gus Xia","orcid":"https://orcid.org/0000-0003-3629-906X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Gus","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103537853","display_name":"Wei\u2010Hsiang Liao","orcid":"https://orcid.org/0000-0003-4113-1894"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Wei-Hsiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitsufuji, Yuki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077484271","display_name":"Simon Dixon","orcid":"https://orcid.org/0000-0002-6098-481X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dixon, Simon","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100635278"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9889000058174133,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9829999804496765,"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":0.6180249452590942},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.36059921979904175},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.351031631231308},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07375642657279968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6180249452590942},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36059921979904175},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.351031631231308},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07375642657279968}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2405.18386","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.18386","pdf_url":"https://arxiv.org/pdf/2405.18386","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.5281/zenodo.17706407","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},{"id":"doi:10.48550/arxiv.2405.18386","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.18386","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.18386","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.18386","pdf_url":"https://arxiv.org/pdf/2405.18386","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311061","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399197752.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,32,65,200],"text-to-music":[3,189],"editing,":[4],"which":[5,48,122],"employ":[6],"text":[7,114],"queries":[8],"to":[9,41,60,89,126,147,167,174],"modify":[10],"music":[11,28,197,202],"(e.g.\\":[12],"by":[13,38,111],"changing":[14],"its":[15],"style":[16],"or":[17,98],"adjusting":[18],"instrumental":[19],"components),":[20],"present":[21],"unique":[22],"challenges":[23],"and":[24,52,73,117,130,134,152,170],"opportunities":[25],"for":[26,155,178],"AI-assisted":[27],"creation.":[29],"Previous":[30],"approaches":[31],"this":[33],"domain":[34],"have":[35],"been":[36],"constrained":[37],"the":[39,71,107,124,136,148,175,186,194],"necessity":[40],"train":[42],"specific":[43,179],"editing":[44,92,190],"models":[45,59,176,199],"from":[46],"scratch,":[47],"is":[49],"both":[50],"resource-intensive":[51],"inefficient;":[53],"other":[54],"research":[55],"uses":[56],"large":[57],"language":[58,198],"predict":[61],"edited":[62,138],"music,":[63],"resulting":[64],"imprecise":[66],"audio":[67,119,131],"reconstruction.":[68],"To":[69],"Combine":[70],"strengths":[72],"address":[74],"these":[75],"limitations,":[76],"we":[77],"introduce":[78],"Instruct-MusicGen,":[79],"a":[80,85,104,113],"novel":[81],"approach":[82,102],"that":[83],"finetunes":[84],"pretrained":[86],"MusicGen":[87,109,150],"model":[88,125,151],"efficiently":[90],"follow":[91],"instructions":[93],"such":[94],"as":[95],"adding,":[96],"removing,":[97],"separating":[99],"stems.":[100],"Our":[101],"involves":[103],"modification":[105],"of":[106,188,196],"original":[108,149],"architecture":[110],"incorporating":[112],"fusion":[115,120],"module":[116],"an":[118],"module,":[121],"allow":[123],"process":[127],"instruction":[128],"texts":[129],"inputs":[132],"concurrently":[133],"yield":[135],"desired":[137],"music.":[139],"Remarkably,":[140],"Instruct-MusicGen":[141],"only":[142,153,184],"introduces":[143],"8%":[144],"new":[145],"parameters":[146],"trains":[154],"5K":[156],"steps,":[157],"yet":[158],"it":[159],"achieves":[160],"superior":[161],"performance":[162,172],"across":[163],"all":[164],"tasks":[165],"compared":[166],"existing":[168],"baselines,":[169],"demonstrates":[171],"comparable":[173],"trained":[177],"tasks.":[180],"This":[181],"advancement":[182],"not":[183],"enhances":[185],"efficiency":[187],"but":[191],"also":[192],"broadens":[193],"applicability":[195],"dynamic":[201],"production":[203],"environments.":[204]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
