{"id":"https://openalex.org/W7108667020","doi":"https://doi.org/10.5281/zenodo.17811347","title":"Aligning Text-to-Music Evaluation with Human Preferences","display_name":"Aligning Text-to-Music Evaluation with Human Preferences","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108667020","doi":"https://doi.org/10.5281/zenodo.17811347"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811347","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811347","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811347","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yichen Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yichen Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zachary  Novack","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zachary  Novack","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Koichi Saito","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koichi Saito","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiatong  Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiatong  Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shinji  Watanabe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji  Watanabe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuki  Mitsufuji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki  Mitsufuji","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"John  Thickstun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John  Thickstun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Chris  Donahue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris  Donahue","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62310538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8555999994277954,"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":0.8555999994277954,"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":0.06040000170469284,"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":0.008999999612569809,"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/metric","display_name":"Metric (unit)","score":0.6777999997138977},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6712999939918518},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5881999731063843},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5551000237464905},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5175999999046326},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4871000051498413},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.47999998927116394},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41359999775886536}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6777999997138977},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6712999939918518},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5817000269889832},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5551000237464905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5299999713897705},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45559999346733093},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41359999775886536},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.375900000333786},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28049999475479126},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811347","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811347","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811347","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811347","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[{"score":0.46356287598609924,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"significant":[1],"recent":[2],"advances":[3],"in":[4,18],"generative":[5],"acoustic":[6],"text-to-music":[7],"(TTM)":[8],"modeling,":[9],"robust":[10],"evaluation":[11],"of":[12,36,67],"these":[13],"models":[14,43],"lags":[15],"behind,":[16],"relying":[17],"particular":[19,54],"on":[20,62,85,122],"the":[21,33,80,116],"popular":[22],"Fr\u00e9chet":[23],"Audio":[24,118],"Distance":[25],"(FAD).":[26],"In":[27],"this":[28,133],"work,":[29],"we":[30],"rigorously":[31],"study":[32],"design":[34],"space":[35],"reference-based":[37],"divergence":[38],"metrics":[39,97],"for":[40,71,144,148],"evaluating":[41,61],"TTM":[42,72],"through":[44],"(1)":[45],"designing":[46],"four":[47],"synthetic":[48,87],"meta-evaluations":[49],"to":[50,53,99],"measure":[51],"sensitivity":[52],"musical":[55,138],"desiderata,":[56,102],"and":[57,60,88,103,150],"(2)":[58],"collecting":[59],"MusicPrefs,":[63],"an":[64],"open-source":[65],"dataset":[66],"pairwise":[68],"human":[69,89,109],"preferences":[70],"systems.":[73],"We":[74,111,130],"find":[75,131],"that":[76,93,132],"not":[77],"only":[78,105],"is":[79],"standard":[81],"FAD":[82],"setup":[83],"inconsistent":[84],"both":[86],"preference":[90],"data,":[91],"but":[92],"nearly":[94],"all":[95],"existing":[96],"fail":[98],"effectively":[100,135],"capture":[101],"are":[104],"weakly":[106],"correlated":[107],"with":[108,155],"perception.":[110],"propose":[112],"a":[113,125],"new":[114],"metric,":[115],"MAUVE":[117],"Divergence":[119],"(MAD),":[120],"computed":[121],"representations":[123],"from":[124],"self-supervised":[126],"audio":[127],"embedding":[128],"model.":[129],"metric":[134],"captures":[136],"diverse":[137],"desiderata":[139],"(average":[140],"rank":[141],"correlation":[142],"0.84":[143],"MAD":[145],"vs.":[146,158],"0.49":[147],"FAD)":[149],"also":[151],"correlates":[152],"more":[153],"strongly":[154],"MusicPrefs":[156],"(0.62":[157],"0.14).":[159]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}