{"id":"https://openalex.org/W4416035844","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1133","title":"Orchestrating Audio: Multi-Agent Framework for Long-Video Audio Synthesis","display_name":"Orchestrating Audio: Multi-Agent Framework for Long-Video Audio Synthesis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035844","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1133"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1133","pdf_url":"https://aclanthology.org/2025.emnlp-main.1133.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1133.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yehang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yehang Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111926973","display_name":"Xinli Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinli Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103435820","display_name":"Xiaojie Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojie Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039668642","display_name":"Doudou Zhang","orcid":"https://orcid.org/0000-0001-8784-5599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Doudou Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101938761","display_name":"Ying-Cong Chen","orcid":"https://orcid.org/0000-0002-9565-8205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying-Cong Chen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32487017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22278","last_page":"22293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.6072999835014343,"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":0.6072999835014343,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.1624000072479248,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.0617000013589859,"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/set","display_name":"Set (abstract data type)","score":0.3093000054359436},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.29789999127388},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2493000030517578},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24330000579357147},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.23589999973773956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6342999935150146},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28220000863075256},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2493000030517578},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24330000579357147},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23589999973773956},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23389999568462372}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1133","pdf_url":"https://aclanthology.org/2025.emnlp-main.1133.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1133","pdf_url":"https://aclanthology.org/2025.emnlp-main.1133.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035844.pdf","grobid_xml":"https://content.openalex.org/works/W4416035844.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video-to-audio":[0],"synthesis,":[1],"which":[2],"generates":[3],"synchronized":[4],"audio":[5,35,77,91,94,124],"for":[6,23],"visual":[7],"content,":[8],"critically":[9],"enhances":[10],"viewer":[11],"immersion":[12],"and":[13,18,37,60,93],"narrative":[14],"coherence":[15],"in":[16,46,51,122],"film":[17],"interactive":[19],"media.However,":[20],"video-to-audio":[21],"dubbing":[22],"long-form":[24],"content":[25],"remains":[26],"an":[27],"unsolved":[28],"challenge":[29],"due":[30,56],"to":[31,57,75],"dynamic":[32],"semantic":[33],"shifts,":[34],"diversity":[36],"the":[38,102],"absence":[39],"of":[40],"dedicated":[41],"datasets.While":[42],"existing":[43],"methods":[44],"excel":[45],"short":[47],"videos,":[48],"they":[49],"falter":[50],"long":[52,109],"scenarios":[53],"(e.g.,":[54],"movies)":[55],"fragmented":[58],"synthesis":[59,82,125],"inadequate":[61],"cross-scene":[62],"consistency.We":[63],"propose":[64],"LVAS-Agent,":[65],"a":[66,71],"multi-agent":[67],"framework":[68],"that":[69,115],"offers":[70],"coordinated,":[72],"multi-component":[73],"approach":[74,79],"long-video":[76,81],"generation.Our":[78],"decomposes":[80],"into":[83],"four":[84],"steps":[85],"including":[86],"scene":[87],"segmentation,":[88],"script":[89],"generation,":[90],"design":[92],"synthesis.To":[95],"enable":[96],"systematic":[97],"evaluation,":[98],"we":[99],"introduce":[100],"LVAS-Bench,":[101],"first":[103],"benchmark":[104],"with":[105],"207":[106],"professionally":[107],"curated":[108],"videos":[110],"spanning":[111],"diverse":[112],"scenarios.Experiments":[113],"show":[114],"our":[116],"method":[117],"outperforms":[118],"state-of-the-art":[119],"V2A":[120],"models":[121],"overall":[123],"quality.":[126]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-11-08T00:00:00"}