{"id":"https://openalex.org/W7148524981","doi":"https://doi.org/10.1109/asru65441.2025.11433844","title":"MMMOS: Multi-domain Multi-axis Audio Quality Assessment","display_name":"MMMOS: Multi-domain Multi-axis Audio Quality Assessment","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148524981","doi":"https://doi.org/10.1109/asru65441.2025.11433844"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11433844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433844","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/A5083437044","display_name":"Yi\u2010Cheng Lin","orcid":"https://orcid.org/0000-0002-5130-5280"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yi-Cheng Lin","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065522357","display_name":"Jia\u2010Hung Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Hung Chen","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132807525","display_name":"Hung-Yi Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083437044"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75323874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8992999792098999,"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/T10860","display_name":"Speech and Audio Processing","score":0.8992999792098999,"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/T11309","display_name":"Music and Audio Processing","score":0.06830000132322311,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.010400000028312206,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/encoder","display_name":"Encoder","score":0.5823000073432922},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.5715000033378601},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5116999745368958},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.49160000681877136},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47780001163482666},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.44519999623298645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6434999704360962},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.5715000033378601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5127000212669373},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.49160000681877136},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47780001163482666},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3716999888420105},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3230000138282776},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C2984588014","wikidata":"https://www.wikidata.org/wiki/Q730675","display_name":"Quantitative assessment","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25119999051094055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11433844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433844","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2963403924","https://openalex.org/W2972359262","https://openalex.org/W2972394484","https://openalex.org/W3160506022","https://openalex.org/W3161480375","https://openalex.org/W3162538529","https://openalex.org/W3207932315","https://openalex.org/W3209984917","https://openalex.org/W4206354073","https://openalex.org/W4221144124","https://openalex.org/W4225956675","https://openalex.org/W4311167834","https://openalex.org/W4400055546","https://openalex.org/W4402112400","https://openalex.org/W4402112435","https://openalex.org/W4403791637","https://openalex.org/W4407098018","https://openalex.org/W4413472064","https://openalex.org/W4415433654","https://openalex.org/W7148506573","https://openalex.org/W7148612566"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"audio":[1,10,45],"quality":[2,46],"estimation":[3],"is":[4],"essential":[5],"for":[6,27],"developing":[7],"and":[8,13,33,60,66,79,81,110,129],"evaluating":[9],"generation,":[11],"retrieval,":[12],"enhancement":[14],"systems.":[15],"Existing":[16],"non-intrusive":[17],"assessment":[18,47],"models":[19],"predict":[20],"a":[21,42,98,111],"single":[22],"Mean":[23],"Opinion":[24],"Score":[25],"(MOS)":[26],"speech,":[28,64],"merging":[29],"diverse":[30],"perceptual":[31],"factors":[32],"failing":[34],"to":[35],"generalize":[36],"beyond":[37],"speech.":[38],"We":[39],"propose":[40],"MMMOS,":[41],"no-reference,":[43],"multidomain":[44],"system":[48],"that":[49],"estimates":[50],"four":[51,87],"orthogonal":[52],"axes:":[53],"Production":[54,56,126],"Quality,":[55],"Complexity,":[57],"Content":[58,61],"Enjoyment,":[59],"Usefulness":[62],"across":[63],"music,":[65],"environmental":[67],"sounds.":[68],"MMMOS":[69,96],"fuses":[70],"frame-level":[71],"embeddings":[72],"from":[73],"three":[74,83,134],"pretrained":[75],"encoders":[76],"(WavLM,":[77],"MuQ,":[78],"M2D)":[80],"evaluates":[82],"aggregation":[84],"strategies":[85],"with":[86],"loss":[88],"functions.":[89],"By":[90],"ensembling":[91],"the":[92,132],"top":[93,133],"eight":[94,125],"models,":[95],"shows":[97],"$\\mathbf{2":[99],"0":[100,103],"-":[101],"3":[102],"\\%}$":[104],"reduction":[105],"in":[106,114,122],"mean":[107],"squared":[108],"error":[109],"4-5%":[112],"increase":[113],"Kendall\u2019s":[115],"$\\tau$":[116],"versus":[117],"baseline,":[118],"gains":[119],"first":[120],"place":[121],"six":[123],"of":[124,137],"Complexity":[127],"metrics,":[128],"ranks":[130],"among":[131],"on":[135],"17":[136],"32":[138],"challenge":[139],"metrics.":[140]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}