{"id":"https://openalex.org/W4410771312","doi":"https://doi.org/10.1109/icasspw65056.2025.11011064","title":"Musimple: A Simplified Music Generation System with Diffusion Transformer","display_name":"Musimple: A Simplified Music Generation System with Diffusion Transformer","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410771312","doi":"https://doi.org/10.1109/icasspw65056.2025.11011064"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011064","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 Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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":null,"display_name":"Zheqi Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zheqi Dai","raw_affiliation_strings":["The Chinese University of Hong Kong,Electronic Engineering"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Electronic Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043683058","display_name":"Hongyu He","orcid":"https://orcid.org/0000-0003-0721-9067"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haolin He","raw_affiliation_strings":["The Chinese University of Hong Kong,Electronic Engineering"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Electronic Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["The Chinese University of Hong Kong,Electronic Engineering"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Electronic Engineering","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1232407,"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":0.9886000156402588,"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":0.9886000156402588,"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":0.9878000020980835,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9327999949455261,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5668829679489136},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44496795535087585},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.30566921830177307},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16204774379730225},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09304344654083252}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5668829679489136},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44496795535087585},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.30566921830177307},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16204774379730225},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09304344654083252}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011064","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 Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2526050071","https://openalex.org/W2970641574","https://openalex.org/W2982753834","https://openalex.org/W4312933868","https://openalex.org/W4372266552","https://openalex.org/W4390872297","https://openalex.org/W4396877837","https://openalex.org/W4406417959","https://openalex.org/W4408345930","https://openalex.org/W4409362462","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6691217105","https://openalex.org/W6733814495","https://openalex.org/W6739901393","https://openalex.org/W6755406732","https://openalex.org/W6757220786","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6785932716","https://openalex.org/W6795288823","https://openalex.org/W6838843145","https://openalex.org/W6849105126","https://openalex.org/W6849517043","https://openalex.org/W6853096648"],"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":{"Music":[0],"generation":[1,39,72],"has":[2],"become":[3],"an":[4],"important":[5],"area":[6],"of":[7,118],"research,":[8],"with":[9,135],"applications":[10],"in":[11,31],"automated":[12],"composition,":[13],"personalized":[14],"soundtracks,":[15],"and":[16,46,57,81,100,114,121,141,147],"virtual":[17],"entertainment.":[18],"Recently,":[19],"diffusion":[20],"models":[21],"such":[22,110],"as":[23,85,111],"Diffusion":[24],"Transformers":[25],"(DiT)":[26],"have":[27],"shown":[28],"promising":[29],"results":[30,125],"generating":[32],"high-quality":[33],"audio.":[34],"However,":[35],"many":[36],"previous":[37],"music":[38],"systems":[40],"rely":[41],"heavily":[42],"on":[43],"large":[44],"datasets":[45],"require":[47],"significant":[48],"computational":[49,102],"resources.":[50],"This":[51],"makes":[52],"them":[53],"challenging":[54],"to":[55],"reproduce":[56],"less":[58],"accessible":[59],"for":[60],"broader":[61],"research.":[62],"To":[63],"address":[64],"these":[65],"limitations,":[66],"we":[67,96],"propose":[68],"a":[69],"simplified":[70],"text-to-music":[71],"system.":[73],"Our":[74,138],"model":[75,107],"uses":[76],"the":[77,86,98],"small-scale":[78],"GTZAN":[79],"dataset":[80],"2D":[82],"mel":[83],"spectrograms":[84],"primary":[87],"audio":[88,133],"representation.":[89],"By":[90],"avoiding":[91],"complex":[92],"components":[93],"like":[94],"VAEs,":[95],"streamline":[97],"architecture":[99],"reduce":[101],"overhead.":[103],"We":[104],"evaluate":[105],"our":[106,128],"using":[108],"metrics":[109],"FAD,":[112],"KL":[113],"CLAP,":[115],"achieving":[116],"scores":[117],"5.0,":[119],"2.31,":[120],"0.18,":[122],"respectively.":[123],"These":[124],"demonstrate":[126],"that":[127],"system":[129],"generates":[130],"musically":[131],"acceptable":[132],"even":[134],"reduced":[136],"data.":[137],"code,":[139],"data,":[140],"pre-trained":[142],"checkpoints":[143],"are":[144],"fully":[145],"open-sourced":[146],"available":[148],"at":[149],"https://huggingface.co/ZheqiDAI/Musimple.":[150]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}