{"id":"https://openalex.org/W4412888548","doi":"https://doi.org/10.18653/v1/2025.findings-acl.360","title":"Generative Music Models\u2019 Alignment with Professional and Amateur Users\u2019 Expectations","display_name":"Generative Music Models\u2019 Alignment with Professional and Amateur Users\u2019 Expectations","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888548","doi":"https://doi.org/10.18653/v1/2025.findings-acl.360"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.360","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.360","pdf_url":"https://aclanthology.org/2025.findings-acl.360.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.360.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100413078","display_name":"Zihao Wang","orcid":"https://orcid.org/0000-0001-8396-3707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101868926","display_name":"Jiaxing Yu","orcid":"https://orcid.org/0009-0008-2162-5110"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxing Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041521616","display_name":"Haoxuan Liu","orcid":"https://orcid.org/0000-0003-2402-9679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoxuan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077156544","display_name":"Zehui Zheng","orcid":"https://orcid.org/0000-0002-1980-1137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehui Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhang Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhang Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733004","display_name":"Shuyu Li","orcid":"https://orcid.org/0000-0002-7586-0430"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007662123","display_name":"Shulei Ji","orcid":"https://orcid.org/0000-0002-9908-136X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shulei Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026251593","display_name":"Kejun Zhang","orcid":"https://orcid.org/0000-0003-4592-1818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kejun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6909","last_page":"6920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9968000054359436,"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":0.9699000120162964,"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/amateur","display_name":"Amateur","score":0.892569363117218},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7202856540679932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6524142026901245},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4315774142742157},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40266919136047363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3528604805469513},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3453415632247925},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3237829804420471},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09998977184295654}],"concepts":[{"id":"https://openalex.org/C2778044066","wikidata":"https://www.wikidata.org/wiki/Q455595","display_name":"Amateur","level":2,"score":0.892569363117218},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7202856540679932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6524142026901245},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4315774142742157},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40266919136047363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3528604805469513},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3453415632247925},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3237829804420471},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09998977184295654},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.360","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.360","pdf_url":"https://aclanthology.org/2025.findings-acl.360.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.360","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.360","pdf_url":"https://aclanthology.org/2025.findings-acl.360.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888548.pdf","grobid_xml":"https://content.openalex.org/works/W4412888548.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"rapid":[4],"advancements":[5],"in":[6,141],"text-to-music":[7],"generation":[8,172],"using":[9,124],"large":[10],"language":[11,154],"models,":[12],"yielding":[13],"notable":[14],"outputs.A":[15],"critical":[16],"challenge":[17],"is":[18],"understanding":[19],"users":[20],"with":[21,57,164,207],"diverse":[22],"musical":[23,62,77,158],"expertise":[24],"and":[25,47,74,90,156,180,187,193,203,210],"generating":[26],"music":[27],"that":[28,34,69,198],"meets":[29],"their":[30],"expectations,":[31],"an":[32],"area":[33],"remains":[35],"underexplored.To":[36],"address":[37],"this":[38],"gap,":[39],"we":[40,130],"introduce":[41],"the":[42,81,96],"novel":[43],"task":[44,51],"of":[45,108,173],"Professional":[46],"Amateur":[48],"Description-to-Song":[49],"Generation.This":[50],"focuses":[52],"on":[53],"aligning":[54,161],"generated":[55,123,162,191],"content":[56,192],"human":[58],"expressions":[59],"from":[60,87],"varying":[61],"proficiency":[63],"levels,":[64],"aiming":[65],"to":[66,76,137,184],"produce":[67],"songs":[68,163,175],"accurately":[70],"meet":[71],"auditory":[72,157,188],"expectations":[73],"adhere":[75],"structural":[78],"conventions.We":[79],"utilized":[80],"MuChin":[82],"dataset,":[83],"which":[84],"contains":[85],"annotations":[86],"both":[88,178,208],"professionals":[89],"amateurs":[91],"for":[92,98,116,119,149],"identical":[93],"songs,":[94],"as":[95],"source":[97],"these":[99],"distinct":[100],"description":[101],"types.We":[102],"also":[103],"collected":[104],"a":[105,133,167],"pre-train":[106],"dataset":[107],"over":[109],"1.5":[110],"million":[111],"songs;":[112],"lyrics":[113,121],"were":[114,122],"included":[115],"some,":[117],"while":[118],"others,":[120],"Automatic":[125],"Speech":[126],"Recognition":[127],"(ASR)":[128],"models.Furthermore,":[129],"propose":[131],"Mu-DiT/MuSiT,":[132],"single-stage":[134],"framework":[135,144],"designed":[136],"enhance":[138],"human-machine":[139],"alignment":[140,206],"song":[142,212],"generation.This":[143],"employs":[145],"Chinese":[146],"MuLan":[147],"(ChinMu)":[148],"cross-modal":[150],"comprehension":[151],"between":[152,190],"natural":[153],"descriptions":[155],"attributes,":[159],"thereby":[160],"user-defined":[165],"outcomes.Concurrently,":[166],"DiT/SiT":[168],"model":[169],"facilitates":[170],"endto-end":[171],"complete":[174],"audio,":[176],"encompassing":[177],"vocals":[179],"instrumentation.We":[181],"proposed":[182],"metrics":[183],"evaluate":[185],"semantic":[186],"discrepancies":[189],"target":[194],"music.Experimental":[195],"results":[196],"demonstrate":[197],"MuDiT/MuSiT":[199],"outperforms":[200],"baseline":[201],"models":[202],"exhibits":[204],"superior":[205],"professional":[209],"amateur":[211],"descriptions.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}