{"id":"https://openalex.org/W4408353668","doi":"https://doi.org/10.1109/icassp49660.2025.10890307","title":"MusicEval: A Generative Music Dataset with Expert Ratings for Automatic Text-to-Music Evaluation","display_name":"MusicEval: A Generative Music Dataset with Expert Ratings for Automatic Text-to-Music Evaluation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353668","doi":"https://doi.org/10.1109/icassp49660.2025.10890307"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100625468","display_name":"Cheng Liu","orcid":"https://orcid.org/0009-0009-6867-1453"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Liu","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460850","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8814-1988"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033737287","display_name":"Jinghua Zhao","orcid":"https://orcid.org/0000-0002-9741-6998"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghua Zhao","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052465353","display_name":"Shiwan Zhao","orcid":"https://orcid.org/0000-0001-5068-025X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwan Zhao","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101791717","display_name":"Hui Bu","orcid":"https://orcid.org/0000-0003-1883-8496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Bu","raw_affiliation_strings":["Beijing AISHELL Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing AISHELL Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["Beijing AISHELL Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing AISHELL Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113361562","display_name":"Jiaming Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhou","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035524175","display_name":"Haoqin Sun","orcid":"https://orcid.org/0000-0002-8554-8969"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqin Sun","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102006082","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0001-9808-0456"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.6402,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.98570202,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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":0.9993000030517578,"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":0.9993000030517578,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9711999893188477,"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/computer-science","display_name":"Computer science","score":0.7071954011917114},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6483232975006104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4275391101837158},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4103752374649048},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.408660888671875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39034533500671387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071954011917114},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6483232975006104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4275391101837158},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4103752374649048},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.408660888671875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39034533500671387}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2972478942","https://openalex.org/W3161480375","https://openalex.org/W3196475561","https://openalex.org/W3198270377","https://openalex.org/W3202278141","https://openalex.org/W4297841702","https://openalex.org/W4372260310","https://openalex.org/W4377140494","https://openalex.org/W4385245566","https://openalex.org/W4385823334","https://openalex.org/W4387969125","https://openalex.org/W4392903114","https://openalex.org/W4392903310","https://openalex.org/W4396877837","https://openalex.org/W4402111705","https://openalex.org/W4402112248","https://openalex.org/W4403780831","https://openalex.org/W6747733185","https://openalex.org/W6779823529","https://openalex.org/W6842893850","https://openalex.org/W6845479124","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6849517043","https://openalex.org/W6849635556","https://openalex.org/W6849739172","https://openalex.org/W6853096648","https://openalex.org/W6853533739","https://openalex.org/W6856202980","https://openalex.org/W6856434366","https://openalex.org/W6860273036","https://openalex.org/W6869945801"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W2374712251","https://openalex.org/W4383031710","https://openalex.org/W3211753092","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,148],"technology":[1],"for":[2,47,142],"generating":[3],"music":[4,67,85,92,114],"from":[5,112],"textual":[6],"descriptions":[7],"has":[8],"seen":[9],"rapid":[10],"advancements.":[11],"However,":[12],"evaluating":[13],"text-to-music":[14],"(TTM)":[15],"systems":[16],"remains":[17],"a":[18,119,139],"significant":[19],"challenge,":[20],"primarily":[21],"due":[22],"to":[23,50,104],"the":[24,57,63,70,73,82,132,135],"difficulty":[25],"of":[26,66,72,134],"balancing":[27],"performance":[28],"and":[29,34,69,77,98,127],"cost":[30],"with":[31,52,109],"existing":[32],"objective":[33],"subjective":[35],"evaluation":[36,59,68],"methods.":[37],"In":[38],"this":[39,125],"paper,":[40],"we":[41,79,117],"propose":[42],"an":[43],"automatic":[44],"assessment":[45,86,121],"task":[46],"TTM":[48,58,146],"models":[49,101],"align":[51],"human":[53],"perception.":[54],"To":[55],"address":[56],"challenges":[60],"posed":[61],"by":[62,95],"professional":[64],"requirements":[65],"complexity":[71],"relationship":[74],"between":[75],"text":[76,106],"music,":[78],"collect":[80],"MusicEval,":[81],"first":[83],"generative":[84],"dataset.":[87],"This":[88],"dataset":[89,149],"contains":[90],"2,748":[91],"clips":[93],"generated":[94],"31":[96],"advanced":[97],"widely":[99],"used":[100],"in":[102,145],"response":[103],"384":[105],"prompts,":[107],"along":[108],"13,740":[110],"ratings":[111],"14":[113],"experts.":[115],"Furthermore,":[116],"design":[118],"CLAP-based":[120],"model":[122],"built":[123],"on":[124],"dataset,":[126],"our":[128],"experimental":[129],"results":[130],"validate":[131],"feasibility":[133],"proposed":[136],"task,":[137],"providing":[138],"valuable":[140],"reference":[141],"future":[143],"development":[144],"evaluation.":[147],"is":[150],"available":[151],"at":[152],"https://www.aishelltech.com/AISHELL_7A.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
