{"id":"https://openalex.org/W4412605354","doi":"https://doi.org/10.1109/tmm.2025.3590912","title":"XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework","display_name":"XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412605354","doi":"https://doi.org/10.1109/tmm.2025.3590912"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3590912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3590912","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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":"Sida Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sida Tian","raw_affiliation_strings":["Tencent, Beijing, China","Tencent, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440826","display_name":"Can Zhang","orcid":"https://orcid.org/0000-0001-9530-5218"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Zhang","raw_affiliation_strings":["Tencent, Beijing, China","Tencent, China"],"raw_orcid":"https://orcid.org/0000-0001-9530-5218","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059519578","display_name":"Wei Yuan","orcid":"https://orcid.org/0000-0001-9357-5716"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yuan","raw_affiliation_strings":["Tencent, Beijing, China","Tencent, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082067089","display_name":"Wei Tan","orcid":"https://orcid.org/0000-0002-6052-4119"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Tan","raw_affiliation_strings":["Tencent, Beijing, China","Tencent, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101797100","display_name":"Wenjie Zhu","orcid":"https://orcid.org/0009-0000-1728-7333"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Zhu","raw_affiliation_strings":["Tencent, Beijing, China","Tencent, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":13.1317,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.98931958,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"6857","last_page":"6871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9932000041007996,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9932000041007996,"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/T11309","display_name":"Music and Audio Processing","score":0.9613999724388123,"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/computer-science","display_name":"Computer science","score":0.8084951639175415},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40034613013267517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084951639175415},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40034613013267517}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3590912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3590912","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2169896877","https://openalex.org/W2194775991","https://openalex.org/W2732026016","https://openalex.org/W2744457411","https://openalex.org/W2772474126","https://openalex.org/W2792351129","https://openalex.org/W2811167645","https://openalex.org/W2887175137","https://openalex.org/W2891757161","https://openalex.org/W2962770929","https://openalex.org/W2964110616","https://openalex.org/W2968379763","https://openalex.org/W2970641574","https://openalex.org/W3015625764","https://openalex.org/W3092879656","https://openalex.org/W3108240585","https://openalex.org/W3175663427","https://openalex.org/W3207149528","https://openalex.org/W3207290297","https://openalex.org/W3213549365","https://openalex.org/W4210698306","https://openalex.org/W4226103472","https://openalex.org/W4310987263","https://openalex.org/W4312814772","https://openalex.org/W4312933868","https://openalex.org/W4362563993","https://openalex.org/W4376607936","https://openalex.org/W4380303621","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4385764283","https://openalex.org/W4387249848","https://openalex.org/W4390873340","https://openalex.org/W4401607896","https://openalex.org/W4402671601"],"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/W4396696052"],"abstract_inverted_index":{"In":[0,163],"recent":[1],"years,":[2],"remarkable":[3],"advancements":[4],"in":[5,13],"artificial":[6],"intelligence-generated":[7],"content":[8,23],"(AIGC)":[9],"have":[10],"been":[11,205],"achieved":[12],"the":[14,31,45,96,112,142,194,210],"fields":[15],"of":[16,33,47,87,98,209,213,221],"image":[17],"synthesis":[18],"and":[19,52,75,81,92,109,123,131,159,182,186],"text":[20],"generation,":[21],"generating":[22],"comparable":[24],"to":[25,44,77,115],"that":[26,173,190],"produced":[27],"by":[28,148],"humans.":[29],"However,":[30],"quality":[32,155],"AI-generated":[34],"music":[35,62,103,133,139,147,171,200],"has":[36,204],"not":[37],"yet":[38],"reached":[39],"this":[40],"standard,":[41],"primarily":[42],"due":[43],"challenge":[46],"effectively":[48],"controlling":[49],"musical":[50],"emotions":[51],"ensuring":[53],"high-quality":[54,82,145],"outputs.":[55],"This":[56],"paper":[57],"presents":[58],"a":[59,121,124,150,168],"generalized":[60],"symbolic":[61,83,102,138,146,170],"generation":[63],"framework,":[64],"XMusic,":[65],"which":[66],"supports":[67],"flexible":[68],"prompts":[69,97],"(i.e.,":[70,105],"images,":[71],"videos,":[72],"texts,":[73],"tags,":[74],"humming)":[76],"generate":[78,116],"emotionally":[79,129],"controllable":[80,130],"music.":[84,118],"XMusic":[85,191,203,222],"consists":[86],"two":[88],"core":[89],"components,":[90],"XProjector":[91,94],"XComposer.":[93],"parses":[95],"various":[99],"modalities":[100],"into":[101],"elements":[104],"emotions,":[106],"genres,":[107],"rhythms":[108],"notes)":[110],"within":[111],"projection":[113],"space":[114],"matching":[117],"XComposer":[119],"contains":[120,174],"Generator":[122,127],"Selector.":[125],"The":[126,218],"generates":[128],"melodious":[132],"based":[134],"on":[135],"our":[136],"innovative":[137],"representation,":[140],"whereas":[141],"Selector":[143],"identifies":[144],"constructing":[149],"multi-task":[151],"learning":[152],"scheme":[153],"involving":[154],"assessment,":[156],"emotion":[157,181],"recognition,":[158],"genre":[160,183],"recognition":[161],"tasks.":[162],"addition,":[164],"we":[165],"build":[166],"XMIDI,":[167],"large-scale":[169],"dataset":[172],"108,023":[175],"MIDI":[176],"files":[177],"annotated":[178],"with":[179,198],"precise":[180],"labels.":[184],"Objective":[185],"subjective":[187],"evaluations":[188],"show":[189],"significantly":[192],"outperforms":[193],"current":[195],"stateof-the-art":[196],"methods":[197],"impressive":[199],"quality.":[201],"Our":[202],"awarded":[206],"as":[207],"one":[208],"nine":[211],"Highlights":[212],"Collectibles":[214],"at":[215],"WAIC":[216],"2023.":[217],"project":[219],"homepage":[220],"is:":[223],"https://xmusicproject.github.io":[224]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}