{"id":"https://openalex.org/W4415524568","doi":"https://doi.org/10.1109/mlsp62443.2025.11204254","title":"From Aesthetics to Human Preferences: Comparative Perspectives of Evaluating Text-to-Music Systems","display_name":"From Aesthetics to Human Preferences: Comparative Perspectives of Evaluating Text-to-Music Systems","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524568","doi":"https://doi.org/10.1109/mlsp62443.2025.11204254"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100823846","display_name":"Huan Zhang","orcid":"https://orcid.org/0000-0001-6987-7554"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huan Zhang","raw_affiliation_strings":["Queen Mary University of London,Centre for Digial Music,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digial Music,United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081551271","display_name":"Jinhua Liang","orcid":"https://orcid.org/0000-0002-4322-6507"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinhua Liang","raw_affiliation_strings":["Queen Mary University of London,Centre for Digial Music,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digial Music,United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Reality Labs,Meta,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs,Meta,France","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Speech and Signal Processing (CVSSP), University of Surrey,Centre for Vision,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Signal Processing (CVSSP), University of Surrey,Centre for Vision,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":null,"display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Queen Mary University of London,Centre for Digial Music,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digial Music,United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.8555999994277954,"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":0.8555999994277954,"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":0.7968000173568726,"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/generative-grammar","display_name":"Generative grammar","score":0.6657000184059143},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5752999782562256},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5623999834060669},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.557200014591217},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.49559998512268066},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47589999437332153}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6657000184059143},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5752999782562256},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5623999834060669},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47589999437332153},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4523000121116638},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4368000030517578},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35929998755455017},{"id":"https://openalex.org/C131503682","wikidata":"https://www.wikidata.org/wiki/Q208365","display_name":"Ethnomusicology","level":3,"score":0.34220001101493835},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3305000066757202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.2671000063419342}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2935170919","https://openalex.org/W3094550259","https://openalex.org/W3120724136","https://openalex.org/W4367359628","https://openalex.org/W4382935141","https://openalex.org/W4388118236","https://openalex.org/W4392902957","https://openalex.org/W4401014602","https://openalex.org/W4403780831","https://openalex.org/W4408345930","https://openalex.org/W4408353668","https://openalex.org/W4408354943","https://openalex.org/W4410986283"],"related_works":[],"abstract_inverted_index":{"Evaluating":[0],"generative":[1,126],"models":[2],"remains":[3],"a":[4,24,105,116],"fundamental":[5],"challenge,":[6],"particularly":[7],"when":[8],"the":[9,29,88,92,95,120],"goal":[10],"is":[11],"to":[12,27,55],"reflect":[13],"human":[14,36,123],"preferences.":[15,37],"In":[16],"this":[17],"paper,":[18],"we":[19,59,103],"use":[20],"music":[21,45,62],"generation":[22,46],"as":[23,72],"case":[25],"study":[26,114],"investigate":[28],"gap":[30],"between":[31],"automatic":[32],"evaluation":[33,97,132],"metrics":[34,70],"and":[35,52,67,77],"We":[38],"conduct":[39],"comparative":[40],"experiments":[41],"across":[42,87,134],"five":[43],"state-of-the-art":[44],"approaches,":[47],"assessing":[48],"both":[49],"perceptual":[50,65],"quality":[51],"distributional":[53],"similarity":[54],"human-composed":[56],"music.":[57],"Specifically,":[58],"evaluate":[60],"synthesis":[61],"from":[63,110],"various":[64],"dimensions":[66],"examine":[68],"reference-based":[69],"such":[71],"Mauve":[73],"Audio":[74,79],"Divergence":[75],"(MAD)":[76],"Kernel":[78],"Distance":[80],"(KAD).":[81],"Our":[82],"findings":[83],"reveal":[84],"significant":[85],"inconsistencies":[86],"different":[89],"metrics,":[90],"highlighting":[91],"limitation":[93],"of":[94,122],"current":[96],"practice.":[98],"To":[99],"support":[100],"further":[101],"research,":[102],"release":[104],"benchmark":[106],"dataset":[107],"comprising":[108],"samples":[109],"multiple":[111],"models.":[112],"This":[113],"provides":[115],"broader":[117],"perspective":[118],"on":[119],"alignment":[121],"preference":[124],"in":[125],"modeling,":[127],"advocating":[128],"for":[129],"more":[130],"human-centered":[131],"strategies":[133],"domains.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}