{"id":"https://openalex.org/W4415539635","doi":"https://doi.org/10.1145/3746027.3758260","title":"AudioSet-R: A Refined AudioSet with Multi-Stage LLM Label Reannotation","display_name":"AudioSet-R: A Refined AudioSet with Multi-Stage LLM Label Reannotation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539635","doi":"https://doi.org/10.1145/3746027.3758260"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3758260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.15429","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yulin Sun","orcid":"https://orcid.org/0009-0001-3717-2223"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulin Sun","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0001-3717-2223","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047948744","display_name":"Qisheng Xu","orcid":"https://orcid.org/0000-0003-4141-5950"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qisheng Xu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0003-4141-5950","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000468857","display_name":"Yi Su","orcid":"https://orcid.org/0000-0001-8794-7376"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Su","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-8794-7376","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779837","display_name":"Qian Zhu","orcid":"https://orcid.org/0009-0001-8663-0382"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Zhu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0001-8663-0382","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051680867","display_name":"Yong Dou","orcid":"https://orcid.org/0000-0002-1256-8934"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Dou","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0002-1256-8934","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727888","display_name":"Xinwang Liu","orcid":"https://orcid.org/0000-0001-9066-1475"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinwang Liu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-9066-1475","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-5997-5169","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":3.0156,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92451052,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"13089","last_page":"13096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9961000084877014,"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":0.9897000193595886,"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/generalizability-theory","display_name":"Generalizability theory","score":0.7404999732971191},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5203999876976013},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4950999915599823},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.48489999771118164},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4163999855518341},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3662000000476837},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.358599990606308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583000063896179},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7404999732971191},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4650000035762787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4431999921798706},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4163999855518341},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3758260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.15429","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.15429","pdf_url":"https://arxiv.org/pdf/2508.15429","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.15429","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.15429","pdf_url":"https://arxiv.org/pdf/2508.15429","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3961492198","display_name":null,"funder_award_id":"2023ZD0121101","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G4560342424","display_name":null,"funder_award_id":"ZZCX-ZZGC-01-04","funder_id":"https://openalex.org/F4320324150","funder_display_name":"National University of Defense Technology"}],"funders":[{"id":"https://openalex.org/F4320324150","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415539635.pdf","grobid_xml":"https://content.openalex.org/works/W4415539635.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2496955520","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2899477876","https://openalex.org/W2931364255","https://openalex.org/W3007113923","https://openalex.org/W3042805811","https://openalex.org/W3094550259","https://openalex.org/W3196974791","https://openalex.org/W3203321135","https://openalex.org/W3206996142","https://openalex.org/W4224917059","https://openalex.org/W4225080353","https://openalex.org/W4304099145","https://openalex.org/W4372266552","https://openalex.org/W4383187404","https://openalex.org/W4386348132","https://openalex.org/W4386918931","https://openalex.org/W4387708435","https://openalex.org/W4387968621","https://openalex.org/W4391992904","https://openalex.org/W4392910434","https://openalex.org/W4396982399","https://openalex.org/W4403491749","https://openalex.org/W4403511362","https://openalex.org/W4403674716","https://openalex.org/W4404519040","https://openalex.org/W4406263636","https://openalex.org/W4406794295","https://openalex.org/W4407116492","https://openalex.org/W4407345301","https://openalex.org/W4407392445","https://openalex.org/W4408353080","https://openalex.org/W4408401184","https://openalex.org/W4408402011","https://openalex.org/W4411403494"],"related_works":[],"abstract_inverted_index":{"AudioSet":[0],"is":[1,133],"a":[2,42,63,94],"widely":[3],"used":[4],"benchmark":[5],"in":[6,32,128],"the":[7,37,55,69,120,125],"audio":[8,106],"research":[9],"community":[10],"and":[11,24,86,112,122],"has":[12],"significantly":[13],"advanced":[14],"various":[15],"audio-related":[16],"tasks.":[17],"However,":[18],"persistent":[19],"issues":[20],"with":[21],"label":[22,56,84,130],"accuracy":[23],"completeness":[25],"remain":[26],"critical":[27],"bottlenecks":[28],"that":[29,46],"limit":[30],"performance":[31,116],"downstream":[33],"applications.":[34],"To":[35],"address":[36],"aforementioned":[38],"challenges,":[39],"we":[40,92],"propose":[41],"three-stage":[43],"reannotation":[44],"framework":[45,61],"harnesses":[47],"general-purpose":[48],"audio-language":[49],"foundation":[50],"models":[51],"to":[52,79],"systematically":[53],"improve":[54],"quality":[57],"of":[58,71,99,124],"AudioSet.":[59],"The":[60],"employs":[62],"cross-modal":[64],"prompting":[65],"strategy,":[66],"inspired":[67],"by":[68],"concept":[70],"prompt":[72],"chaining,":[73],"wherein":[74],"prompts":[75],"are":[76],"sequentially":[77],"composed":[78],"execute":[80],"subtasks":[81],"(audio":[82],"comprehension,":[83],"synthesis,":[85],"semantic":[87],"alignment).":[88],"Leveraging":[89],"this":[90],"framework,":[91],"construct":[93],"high-quality,":[95],"structured":[96],"relabeled":[97],"version":[98],"AudioSet-R.":[100],"Extensive":[101],"experiments":[102],"conducted":[103],"on":[104],"representative":[105],"classification":[107],"models-including":[108],"AST,":[109],"PANNs,":[110],"SSAST,":[111],"AudioMAE-consistently":[113],"demonstrate":[114],"substantial":[115],"improvements,":[117],"thereby":[118],"validating":[119],"generalizability":[121],"effectiveness":[123],"proposed":[126],"approach":[127],"enhancing":[129],"reliability.The":[131],"code":[132],"publicly":[134],"available":[135],"at:":[136],"https://github.com/colaudiolab/AudioSet-R.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}