{"id":"https://openalex.org/W7148392549","doi":"https://doi.org/10.1109/asru65441.2025.11434795","title":"ASTAR-NTU solution to AudioMOS Challenge 2025 Track1","display_name":"ASTAR-NTU solution to AudioMOS Challenge 2025 Track1","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148392549","doi":"https://doi.org/10.1109/asru65441.2025.11434795"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434795","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/A5092905575","display_name":"Fabian Ritter-Gutierrez","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Fabian Ritter-Gutierrez","raw_affiliation_strings":["Institute for Infocomm Research (A* STAR)"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (A* STAR)","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042155634","display_name":"Y C. Lin","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":"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/A5106294622","display_name":"J. T. Wei","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":"Jui-Chiang Wei","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/A5021413708","display_name":"Jhm Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jeremy H.M. Wong","raw_affiliation_strings":["Institute for Infocomm Research (A* STAR)"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (A* STAR)","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132795316","display_name":"Nancy F. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy F. Chen","raw_affiliation_strings":["Institute for Infocomm Research (A* STAR)"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (A* STAR)","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"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":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5092905575"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75755536,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.05959999933838844,"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"}},"topics":[{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.05959999933838844,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.03680000081658363,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.028200000524520874,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/set","display_name":"Set (abstract data type)","score":0.25949999690055847},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2370000034570694},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.23489999771118164},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.227400004863739},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.22089999914169312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32190001010894775},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2370000034570694},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.23489999771118164},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.227400004863739},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.22089999914169312},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2199999988079071},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.21709999442100525},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.21389999985694885},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.210099995136261}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434795","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":9,"referenced_works":["https://openalex.org/W2079735306","https://openalex.org/W3097760447","https://openalex.org/W4255455317","https://openalex.org/W4372260310","https://openalex.org/W4385152092","https://openalex.org/W4396877837","https://openalex.org/W4402112411","https://openalex.org/W4404577625","https://openalex.org/W4413472064"],"related_works":[],"abstract_inverted_index":{"Evaluation":[0],"of":[1,11,92,127,140],"text-to-music":[2],"systems":[3],"is":[4,21],"constrained":[5],"by":[6],"the":[7,36,39,69,78,89,108,153],"cost":[8],"and":[9,38,57,62,71,80,131,146],"availability":[10],"collecting":[12],"experts":[13],"for":[14,129,133],"assessment.":[15],"AudioMOS":[16],"2025":[17],"Challenge":[18],"track":[19],"1":[20],"created":[22],"to":[23,99,136],"automatically":[24],"predict":[25],"music":[26],"impression":[27],"(MI)":[28],"as":[29,31,60,83],"well":[30],"text":[32,63,72],"alignment":[33],"(TA)":[34],"between":[35],"prompt":[37],"generated":[40],"musical":[41],"piece.":[42],"This":[43],"paper":[44],"reports":[45],"our":[46],"winning":[47],"system,":[48],"which":[49],"uses":[50],"a":[51,84,100,104,112,120,137],"dual-branch":[52],"architecture":[53],"with":[54,116],"pre-trained":[55],"MuQ":[56],"RoBERTa":[58],"models":[59],"audio":[61,70],"encoders.":[64],"A":[65],"cross-attention":[66],"mechanism":[67],"fuses":[68],"representations.":[73],"For":[74],"training,":[75],"we":[76],"reframe":[77],"MI":[79,130,144],"TA":[81,150],"prediction":[82],"classification":[85],"task.":[86],"To":[87],"incorporate":[88],"ordinal":[90],"nature":[91],"MOS":[93],"scores,":[94],"one-hot":[95],"labels":[96],"are":[97],"converted":[98],"soft":[101],"distribution":[102],"using":[103],"Gaussian":[105],"kernel.":[106],"On":[107],"official":[109],"test":[110],"set,":[111],"single":[113],"model":[114],"trained":[115],"this":[117],"method":[118],"achieves":[119],"system-level":[121],"Spearman\u2019s":[122],"Rank":[123],"Correlation":[124],"Coefficient":[125],"(SRCC)":[126],"0.991":[128],"0.952":[132],"TA,":[134],"corresponding":[135],"relative":[138],"improvement":[139],"$21.21":[141],"\\%$":[142,148],"in":[143,149],"SRCC":[145,151],"$31.47":[147],"over":[152],"challenge":[154],"baseline.":[155]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}