{"id":"https://openalex.org/W7148612566","doi":"https://doi.org/10.1109/asru65441.2025.11434623","title":"Meta Audiobox Aesthetics: Unified Automatic Assessment for Speech, Music and Sound","display_name":"Meta Audiobox Aesthetics: Unified Automatic Assessment for Speech, Music and Sound","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148612566","doi":"https://doi.org/10.1109/asru65441.2025.11434623"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132755290","display_name":"Andros Tjandra","orcid":null},"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":true,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132793006","display_name":"Yi-Chiao Wu","orcid":null},"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":"Yi-Chiao Wu","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113082671","display_name":"Baishan Guo","orcid":null},"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":"Baishan Guo","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132735370","display_name":"John Hoffman","orcid":null},"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":"John Hoffman","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132775944","display_name":"Brian Ellis","orcid":null},"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":"Brian Ellis","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108691882","display_name":"Apoorv Vyas","orcid":null},"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":"Apoorv Vyas","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132761402","display_name":"Bowen Shi","orcid":null},"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":"Bowen Shi","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079533447","display_name":"Sanyuan Chen","orcid":"https://orcid.org/0000-0002-3082-6052"},"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":"Sanyuan Chen","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108829255","display_name":"Matt Le","orcid":null},"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":"Matt Le","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059223364","display_name":"Nick Zacharov","orcid":null},"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":"Nick Zacharov","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112921393","display_name":"Carleigh Wood","orcid":null},"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":"Carleigh Wood","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103238713","display_name":"Ann Lee","orcid":"https://orcid.org/0000-0002-0840-4988"},"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":"Ann Lee","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132773444","display_name":"Wei-Ning Hsu","orcid":null},"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":"Wei-Ning Hsu","raw_affiliation_strings":["FAIR at Meta, Reality Labs at Meta,USA"],"affiliations":[{"raw_affiliation_string":"FAIR at Meta, Reality Labs at Meta,USA","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5132755290"],"corresponding_institution_ids":["https://openalex.org/I4210128585"],"apc_list":null,"apc_paid":null,"fwci":18.1854,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.99415311,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.13199999928474426,"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":0.13199999928474426,"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":0.121799997985363,"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"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.08349999785423279,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.531499981880188},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.31839999556541443},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3111000061035156},{"id":"https://openalex.org/keywords/sound-analysis","display_name":"Sound analysis","score":0.28780001401901245},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.27059999108314514}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5259000062942505},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34200000762939453},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C2984030306","wikidata":"https://www.wikidata.org/wiki/Q4819857","display_name":"Sound analysis","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5328768491744995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2593116425","https://openalex.org/W2963403924","https://openalex.org/W2972359262","https://openalex.org/W2972394484","https://openalex.org/W2972419867","https://openalex.org/W3016160783","https://openalex.org/W3037038648","https://openalex.org/W3161480375","https://openalex.org/W3196225973","https://openalex.org/W3196475561","https://openalex.org/W3202278141","https://openalex.org/W3209984917","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4372260310","https://openalex.org/W4372260337","https://openalex.org/W4382135514","https://openalex.org/W4385245566","https://openalex.org/W4385822628","https://openalex.org/W4387969148","https://openalex.org/W4391021629","https://openalex.org/W4395959004","https://openalex.org/W4402112400","https://openalex.org/W4402112435","https://openalex.org/W4406461503","https://openalex.org/W4406461865"],"related_works":[],"abstract_inverted_index":{"Quantifying":[0],"audio":[1,42,86,115],"aesthetics":[2,43,116],"is":[3],"challenging":[4],"due":[5],"to":[6,24,124],"its":[7],"subjective":[8],"nature,":[9],"influenced":[10],"by":[11],"human":[12,21,45,71,94],"perception":[13],"and":[14,26,57,77,99,122,128],"cultural":[15],"context.":[16],"Traditional":[17],"methods":[18],"rely":[19],"on":[20],"listeners,":[22],"leading":[23],"inconsistencies":[25],"high":[27],"resource":[28],"demands.":[29],"This":[30,107],"paper":[31],"addresses":[32],"the":[33,112],"growing":[34],"need":[35],"for":[36,51,83],"automated":[37],"systems":[38,48],"capable":[39],"of":[40,114],"predicting":[41],"without":[44],"intervention.":[46],"Such":[47],"are":[49,91],"crucial":[50],"applications":[52],"like":[53],"data":[54],"filtering,":[55],"pseudo-labeling,":[56],"evaluating":[58],"generative":[59],"models.In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"new":[65],"annotation":[66],"guidelines":[67],"that":[68],"break":[69],"down":[70],"listening":[72],"perspectives":[73],"into":[74],"four":[75],"axes":[76],"develop":[78],"no-reference,":[79],"peritem":[80],"prediction":[81],"models":[82,90,121],"more":[84],"nuanced":[85],"quality":[87],"assessment.":[88],"Our":[89],"evaluated":[92],"against":[93],"mean":[95],"opinion":[96],"scores":[97],"(MOS)":[98],"existing":[100],"methods,":[101],"demonstrating":[102],"comparable":[103],"or":[104],"superior":[105],"performance.":[106],"research":[108],"not":[109],"only":[110],"advances":[111],"field":[113],"but":[117],"also":[118],"provides":[119],"open-source":[120],"datasets":[123],"facilitate":[125],"future":[126],"work":[127],"benchmarking.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}