{"id":"https://openalex.org/W7133930723","doi":"https://doi.org/10.1145/3800682","title":"A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives","display_name":"A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives","publication_year":2026,"publication_date":"2026-03-05","ids":{"openalex":"https://openalex.org/W7133930723","doi":"https://doi.org/10.1145/3800682"},"language":"en","primary_location":{"id":"doi:10.1145/3800682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800682","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3800682","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shuyu Li","orcid":"https://orcid.org/0009-0009-3452-1641"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyu Li","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":"https://orcid.org/0009-0009-3452-1641","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007662123","display_name":"Shulei Ji","orcid":"https://orcid.org/0000-0002-9908-136X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulei Ji","raw_affiliation_strings":["Innovation Center of Yangtze River Delta, Zhejiang University","Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-9908-136X","affiliations":[{"raw_affiliation_string":"Innovation Center of Yangtze River Delta, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zihao Wang","orcid":"https://orcid.org/0000-0002-5613-3262"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Wang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-5613-3262","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002666984","display_name":"Songruoyao Wu","orcid":"https://orcid.org/0000-0002-0760-6289"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songruoyao Wu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-0760-6289","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaxing Yu","orcid":"https://orcid.org/0009-0008-2162-5110"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxing Yu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":"https://orcid.org/0009-0008-2162-5110","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128193100","display_name":"Kejun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejun Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University","Innovation Center of Yangtze River Delta, Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-0778-2303","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"Innovation Center of Yangtze River Delta, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0937,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95517595,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"58","issue":"11","first_page":"1","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.42890000343322754,"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":0.42890000343322754,"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":0.20990000665187836,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06270000338554382,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.7157999873161316},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4645000100135803},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4388999938964844},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.3458999991416931},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.262800008058548},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.25999999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942000031471252},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7157999873161316},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4645000100135803},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C198477413","wikidata":"https://www.wikidata.org/wiki/Q7647069","display_name":"Survey data collection","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3800682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800682","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3800682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800682","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G111693571","display_name":null,"funder_award_id":"62272409","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2623550831","https://openalex.org/W2760103357","https://openalex.org/W2809621972","https://openalex.org/W2811167645","https://openalex.org/W2898827701","https://openalex.org/W2899724567","https://openalex.org/W2962730651","https://openalex.org/W2962865004","https://openalex.org/W2962970472","https://openalex.org/W2963076818","https://openalex.org/W2963341956","https://openalex.org/W2963524571","https://openalex.org/W2963925437","https://openalex.org/W2968379763","https://openalex.org/W2970641574","https://openalex.org/W2972478942","https://openalex.org/W3034625979","https://openalex.org/W3035180180","https://openalex.org/W3092850823","https://openalex.org/W3092879656","https://openalex.org/W3112317145","https://openalex.org/W3174868683","https://openalex.org/W3175663427","https://openalex.org/W3189200702","https://openalex.org/W3197273793","https://openalex.org/W3203711169","https://openalex.org/W3207290297","https://openalex.org/W3213549365","https://openalex.org/W4214612132","https://openalex.org/W4285428803","https://openalex.org/W4312933868","https://openalex.org/W4313021454","https://openalex.org/W4367359628","https://openalex.org/W4372266552","https://openalex.org/W4377140494","https://openalex.org/W4380303621","https://openalex.org/W4381786045","https://openalex.org/W4382240060","https://openalex.org/W4385567278","https://openalex.org/W4386071707","https://openalex.org/W4389371446","https://openalex.org/W4389519533","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4390873340","https://openalex.org/W4391407078","https://openalex.org/W4391924849","https://openalex.org/W4394647967","https://openalex.org/W4399743538","https://openalex.org/W4401023606","https://openalex.org/W4402727350","https://openalex.org/W4404965756","https://openalex.org/W4409362690","https://openalex.org/W7133185223","https://openalex.org/W7133219565","https://openalex.org/W7133221421","https://openalex.org/W7133244780","https://openalex.org/W7133260402"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,34,73,79],"rapid":[2],"development":[3],"of":[4],"artificial":[5],"intelligence,":[6],"music":[7],"generation":[8,48],"has":[9],"evolved":[10],"from":[11],"single-modal":[12],"to":[13,67],"cross-modal":[14],"approaches":[15],"and":[16,44,56,63,86,89],"is":[17],"gradually":[18],"moving":[19],"toward":[20],"multi-modal":[21,57],"fusion.":[22],"This":[23],"survey":[24,74],"systematically":[25],"reviews":[26],"this":[27],"developmental":[28],"trajectory.":[29],"The":[30],"discussion":[31],"begins":[32],"with":[33],"representation":[35],"methods":[36],"for":[37,93],"key":[38,61],"modalities,":[39],"including":[40,81],"audio,":[41],"symbolic,":[42],"text,":[43],"visual":[45],"data.":[46],"Music":[47],"techniques":[49],"are":[50,70],"then":[51],"organized":[52],"across":[53],"single-modal,":[54],"cross-modal,":[55],"settings.":[58],"In":[59],"addition,":[60],"datasets":[62],"evaluation":[64,87],"methodologies":[65],"relevant":[66],"these":[68],"tasks":[69],"compiled.":[71],"Finally,":[72],"discusses":[75],"core":[76],"challenges":[77],"in":[78],"field,":[80],"modal":[82],"fusion,":[83],"data":[84],"scarcity,":[85],"frameworks,":[88],"outlines":[90],"potential":[91],"directions":[92],"future":[94],"research.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2026-03-06T00:00:00"}
