{"id":"https://openalex.org/W4415536941","doi":"https://doi.org/10.1145/3746027.3755831","title":"DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis","display_name":"DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536941","doi":"https://doi.org/10.1145/3746027.3755831"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755831","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755831","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wenjie Tian","orcid":"https://orcid.org/0009-0009-3859-0927"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Tian","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0009-3859-0927","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-9275-523X","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1036-7888","affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024679838","display_name":"Zhixian Zhao","orcid":"https://orcid.org/0000-0002-1136-8279"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixian Zhao","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-1136-8279","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zihao Chen","orcid":"https://orcid.org/0009-0005-5413-6725"},"institutions":[{"id":"https://openalex.org/I4210154361","display_name":"Shanghai Jian Qiao University","ror":"https://ror.org/04xdqtw10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154361"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Chen","raw_affiliation_strings":["Giant Network Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-5413-6725","affiliations":[{"raw_affiliation_string":"Giant Network Inc., Shanghai, China","institution_ids":["https://openalex.org/I4210154361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111268242","display_name":"Chaofan Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I4210154361","display_name":"Shanghai Jian Qiao University","ror":"https://ror.org/04xdqtw10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154361"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaofan Ding","raw_affiliation_strings":["Giant Network Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-2051-4538","affiliations":[{"raw_affiliation_string":"Giant Network Inc., Shanghai, China","institution_ids":["https://openalex.org/I4210154361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021368755","display_name":"Xinhan Di","orcid":"https://orcid.org/0009-0001-8855-8628"},"institutions":[{"id":"https://openalex.org/I4210154361","display_name":"Shanghai Jian Qiao University","ror":"https://ror.org/04xdqtw10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154361"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhan Di","raw_affiliation_strings":["Giant Network Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-8855-8628","affiliations":[{"raw_affiliation_string":"Giant Network Inc., Shanghai, China","institution_ids":["https://openalex.org/I4210154361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071414891","display_name":"J. P. Zheng","orcid":"https://orcid.org/0009-0003-2602-2910"},"institutions":[{"id":"https://openalex.org/I4210154361","display_name":"Shanghai Jian Qiao University","ror":"https://ror.org/04xdqtw10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154361"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Zheng","raw_affiliation_strings":["Giant Network Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-2602-2910","affiliations":[{"raw_affiliation_string":"Giant Network Inc., Shanghai, China","institution_ids":["https://openalex.org/I4210154361"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104234552","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0002-5406-2376"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-5406-2376","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10671","last_page":"10680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5562000274658203},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5320000052452087},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49129998683929443},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4431000053882599},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.41690000891685486},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.39590001106262207},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3871000111103058},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3747999966144562},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.36090001463890076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194000124931335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6262999773025513},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4431000053882599},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.33970001339912415},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.29589998722076416},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27070000767707825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755831","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755831","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3015371781","https://openalex.org/W3094550259","https://openalex.org/W4386071707"],"related_works":[],"abstract_inverted_index":{"While":[0],"recent":[1],"video-to-audio":[2],"(V2A)":[3],"models":[4],"can":[5],"generate":[6],"realistic":[7],"background":[8,39,76,151],"audio":[9,40,77],"from":[10],"visual":[11],"input,":[12],"they":[13],"largely":[14],"overlook":[15],"speech,":[16],"an":[17],"essential":[18],"part":[19],"of":[20,157],"many":[21],"video":[22],"soundtracks.":[23],"This":[24],"paper":[25],"proposes":[26],"a":[27,44,53,58,64,67,105,126],"new":[28],"task,":[29],"video-to-soundtrack":[30],"(V2ST)":[31],"generation,":[32],"which":[33],"aims":[34],"to":[35,92,99],"jointly":[36],"produce":[37],"synchronized":[38],"and":[41,70,78,88,95,131,144,150,154],"speech":[42,79,149],"within":[43],"unified":[45,54],"framework.":[46],"To":[47],"tackle":[48],"V2ST,":[49],"we":[50,103,116],"introduce":[51,117],"DualDub,":[52],"framework":[55],"built":[56],"on":[57],"multimodal":[59,65,113],"language":[60],"model":[61],"that":[62,109,137],"integrates":[63],"encoder,":[66],"cross-modal":[68,84],"aligner,":[69],"dual":[71],"decoding":[72],"heads":[73],"for":[74,122],"simultaneous":[75],"generation.":[80],"Specifically,":[81],"our":[82],"proposed":[83],"aligner":[85],"employs":[86],"causal":[87],"non-causal":[89],"attention":[90],"mechanisms":[91],"improve":[93],"synchronization":[94],"acoustic":[96],"harmony.":[97],"Besides,":[98],"handle":[100],"data":[101],"scarcity,":[102],"design":[104],"curriculum":[106],"learning":[107],"strategy":[108],"progressively":[110],"builds":[111],"the":[112,119],"capability.":[114],"Finally,":[115],"DualBench,":[118],"first":[120],"benchmark":[121],"V2ST":[123],"evaluation":[124],"with":[125,147],"carefully":[127],"curated":[128],"test":[129],"set":[130],"comprehensive":[132],"metrics.":[133],"Experimental":[134],"results":[135],"demonstrate":[136],"DualDub":[138,158],"achieves":[139],"state-of-the-art":[140],"performance,":[141],"generating":[142],"high-quality":[143],"well-synchronized":[145],"soundtracks":[146],"both":[148],"audio.":[152],"DualBench":[153],"generated":[155],"samples":[156],"are":[159],"available":[160],"at":[161],"https://github.com/wjtian-wonderful/DualBench.":[162]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}