{"id":"https://openalex.org/W7148471955","doi":"https://doi.org/10.1109/asru65441.2025.11434767","title":"DyMEvalNet: Dynamic Text-Audio-Personalization Fusion for Multimodal Music Quality Assessment","display_name":"DyMEvalNet: Dynamic Text-Audio-Personalization Fusion for Multimodal Music Quality Assessment","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148471955","doi":"https://doi.org/10.1109/asru65441.2025.11434767"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434767","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/A5101293970","display_name":"Xiaoxun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoxun Wu","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043390035","display_name":"Kailai Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088000","display_name":"Ningbo University of Finance & Economics","ror":"https://ror.org/0085x3f43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210088000"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kailai Shen","raw_affiliation_strings":["Juphoon System Software Co., Ltd,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Juphoon System Software Co., Ltd,Ningbo,China","institution_ids":["https://openalex.org/I4210088000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079415014","display_name":"Yuheng Huang","orcid":"https://orcid.org/0009-0006-1575-1466"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuheng Huang","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368058","display_name":"Na Li","orcid":"https://orcid.org/0000-0002-0392-6672"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naiyuan Li","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132758866","display_name":"Diqun Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Diqun Yan","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China"],"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China","institution_ids":["https://openalex.org/I109935558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101293970"],"corresponding_institution_ids":["https://openalex.org/I109935558"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7529817,"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/T11309","display_name":"Music and Audio Processing","score":0.8964999914169312,"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":0.8964999914169312,"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":0.027499999850988388,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.015300000086426735,"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/quality-assessment","display_name":"Quality assessment","score":0.546500027179718},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46129998564720154},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.37720000743865967},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.3181999921798706},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.2913999855518341}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5859000086784363},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.546500027179718},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38449999690055847},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32440000772476196},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434767","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5016708374023438}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2939156090","https://openalex.org/W2963403924","https://openalex.org/W2972394484","https://openalex.org/W3161558238","https://openalex.org/W3198270377","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W4372260310","https://openalex.org/W4372260534","https://openalex.org/W4385895691","https://openalex.org/W4392902957","https://openalex.org/W4392904615","https://openalex.org/W4392908926","https://openalex.org/W4393178509","https://openalex.org/W4402111636","https://openalex.org/W4402111705","https://openalex.org/W4402112400","https://openalex.org/W4406138136","https://openalex.org/W4408353668"],"related_works":[],"abstract_inverted_index":{"Text-to-music":[0],"(TTM)":[1],"generation":[2],"has":[3],"gained":[4],"significant":[5],"attention":[6],"for":[7,27,59,97,110],"its":[8],"ability":[9],"to":[10,73],"produce":[11],"customized":[12],"music":[13,30,42,99,122],"from":[14],"textual":[15,111],"prompts.":[16],"However,":[17],"current":[18],"methods":[19],"lack":[20],"objective":[21],"standards":[22],"and":[23,69,108,129],"semantic":[24,130],"alignment":[25],"metrics":[26],"evaluating":[28],"generated":[29],"quality.":[31],"To":[32],"address":[33],"this":[34],"issue,":[35],"we":[36],"propose":[37],"DyMEval-Net,":[38],"a":[39,48],"dynamic":[40],"multimodal":[41],"quality":[43,100,123],"assessment":[44],"model":[45,115],"based":[46],"on":[47,79],"novel":[49],"three-branch":[50],"architecture":[51],"that":[52],"incorporates":[53],"listener":[54,71],"personalization":[55],"into":[56],"TTM":[57],"evaluation":[58],"the":[60,80,104],"first":[61],"time.":[62],"DyMEvalNet":[63,83],"integrates":[64],"audio":[65,127],"features,":[66],"text":[67],"embeddings,":[68],"personalized":[70],"embeddings":[72],"jointly":[74],"process":[75],"audio-text":[76],"semantics.":[77],"Evaluated":[78],"MusicEval":[81],"dataset,":[82],"achieves":[84],"state-of-the-art":[85],"performance,":[86],"improving":[87],"utterance-level":[88],"Spearman":[89],"Rank":[90],"Correlation":[91],"Coefficient":[92],"(SRCC)":[93],"scores":[94],"by":[95,124],"19.97%":[96],"overall":[98],"(ranking":[101],"second":[102],"in":[103,119],"AudioMOS":[105],"Challenge":[106],"2025)":[107],"18.27%":[109],"alignment.":[112,131],"The":[113],"proposed":[114],"demonstrates":[116],"robust":[117],"effectiveness":[118],"assessing":[120],"TTM-generated":[121],"simultaneously":[125],"considering":[126],"fidelity":[128]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}