{"id":"https://openalex.org/W4414141797","doi":"https://doi.org/10.1109/icmew68306.2025.11152114","title":"Multitrack Music Generation Combining Transformer and Diffusion Model","display_name":"Multitrack Music Generation Combining Transformer and Diffusion Model","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4414141797","doi":"https://doi.org/10.1109/icmew68306.2025.11152114"},"language":"en","primary_location":{"id":"doi:10.1109/icmew68306.2025.11152114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5013704823","display_name":"Luntian Mou","orcid":"https://orcid.org/0000-0002-1551-4448"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Luntian Mou","raw_affiliation_strings":["Beijing University of Technology,Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence,School of Information Science and Technology"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence,School of Information Science and Technology","institution_ids":["https://openalex.org/I37796252","https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683001","display_name":"Yuliang Zhang","orcid":"https://orcid.org/0000-0002-9413-0900"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuliang Zhang","raw_affiliation_strings":["Beijing University of Technology,Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence,School of Information Science and Technology"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence,School of Information Science and Technology","institution_ids":["https://openalex.org/I37796252","https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029309401","display_name":"Yihan Sun","orcid":"https://orcid.org/0009-0002-9178-6565"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihan Sun","raw_affiliation_strings":["Beijing University of Technology,Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence,School of Information Science and Technology"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence,School of Information Science and Technology","institution_ids":["https://openalex.org/I37796252","https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102972678","display_name":"Feng Gao","orcid":"https://orcid.org/0000-0001-8391-8279"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Gao","raw_affiliation_strings":["Peking University,School of Arts"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Arts","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101205208","display_name":"Yong Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xiang","raw_affiliation_strings":["Peking University,School of Arts"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Arts","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013704823"],"corresponding_institution_ids":["https://openalex.org/I125839683","https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31868997,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9972000122070312,"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/T10860","display_name":"Speech and Audio Processing","score":0.9649999737739563,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7311000227928162},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.44029998779296875},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4156000018119812},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4000999927520752},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3190999925136566},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.30970001220703125},{"id":"https://openalex.org/keywords/scale-model","display_name":"Scale model","score":0.30329999327659607}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7311000227928162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.51910001039505},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4000999927520752},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3961000144481659},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C152588345","wikidata":"https://www.wikidata.org/wiki/Q6498959","display_name":"Scale model","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.29499998688697815},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26660001277923584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew68306.2025.11152114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2559110679","https://openalex.org/W2772474126","https://openalex.org/W2919624000","https://openalex.org/W2991108091","https://openalex.org/W3036167779","https://openalex.org/W3049272330","https://openalex.org/W3099378280","https://openalex.org/W3129651364","https://openalex.org/W3209794146","https://openalex.org/W4280589076","https://openalex.org/W4287250916","https://openalex.org/W4293998390","https://openalex.org/W4307008216","https://openalex.org/W4372259826","https://openalex.org/W4375869480","https://openalex.org/W4377140494","https://openalex.org/W4390929260","https://openalex.org/W4394864422"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2864363823"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,9,99,109],"generative":[3],"models":[4],"have":[5],"made":[6],"remarkable":[7],"progress":[8],"music":[10,24,39,133],"generation.":[11],"However,":[12],"since":[13],"most":[14],"existing":[15],"methods":[16],"focus":[17],"on":[18,43,117,141],"generating":[19,22],"single-track":[20],"music,":[21,66],"multitrack":[23,65,97,132],"with":[25,130],"rich":[26],"attributes":[27],"remains":[28],"a":[29,37,85],"challenging":[30],"task.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35],"propose":[36],"novel":[38],"generation":[40,93,134],"method":[41,138],"based":[42],"the":[44,47,50,54,68,92,136],"combination":[45],"of":[46],"Transformer":[48,55],"and":[49,67,76,101,126],"diffusion":[51,69,111],"model.":[52],"Specifically,":[53],"module":[56],"is":[57,71,89],"adopted":[58],"to":[59,73,95],"conduct":[60,114],"structural":[61],"representation":[62],"learning":[63],"for":[64],"model":[70],"utilized":[72],"gradually":[74],"denoise":[75],"generate":[77],"structured":[78],"music.":[79],"To":[80],"further":[81],"enhance":[82],"inter-track":[83],"coherence,":[84],"track":[86,105],"alignment":[87],"loss":[88],"introduced":[90],"during":[91],"process":[94],"enforce":[96],"consistency":[98],"rhythm":[100],"dynamics,":[102],"effectively":[103],"resolving":[104],"coordination":[106],"issues":[107],"inherent":[108],"traditional":[110],"models.":[112],"We":[113],"objective":[115],"experiments":[116],"evaluation":[118],"metrics,":[119],"namely":[120],"pitch":[121],"class":[122],"entropy,":[123],"scale":[124],"consistency,":[125],"groove":[127],"consistency.":[128],"Compared":[129],"previous":[131],"methods,":[135],"proposed":[137],"performs":[139],"better":[140],"these":[142],"metrics.":[143]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}