{"id":"https://openalex.org/W4408356092","doi":"https://doi.org/10.1109/icassp49660.2025.10890403","title":"Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidance","display_name":"Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidance","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356092","doi":"https://doi.org/10.1109/icassp49660.2025.10890403"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091899643","display_name":"Yaoyun Zhang","orcid":"https://orcid.org/0000-0001-9220-3101"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaoyun Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025827045","display_name":"Xuenan Xu","orcid":"https://orcid.org/0000-0001-8718-1278"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuenan Xu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109064838","display_name":"Mengyue Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyue Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091899643"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.8097,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8916868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.8790000081062317,"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":0.8790000081062317,"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/T11309","display_name":"Music and Audio Processing","score":0.8726999759674072,"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/computer-science","display_name":"Computer science","score":0.7483236789703369},{"id":"https://openalex.org/keywords/foley","display_name":"Foley","score":0.7447424530982971},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6064406633377075},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4433864653110504},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4279441237449646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40166306495666504},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.27606552839279175},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2564937472343445},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12924528121948242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483236789703369},{"id":"https://openalex.org/C110446960","wikidata":"https://www.wikidata.org/wiki/Q762316","display_name":"Foley","level":2,"score":0.7447424530982971},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6064406633377075},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4433864653110504},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4279441237449646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40166306495666504},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.27606552839279175},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2564937472343445},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12924528121948242},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2526050071","https://openalex.org/W2962714319","https://openalex.org/W2972478942","https://openalex.org/W3015371781","https://openalex.org/W3046890131","https://openalex.org/W3094550259","https://openalex.org/W3162999565","https://openalex.org/W3163843406","https://openalex.org/W4284898017","https://openalex.org/W4312538130","https://openalex.org/W4372260310","https://openalex.org/W4372348103","https://openalex.org/W4375868912","https://openalex.org/W4386071707","https://openalex.org/W4386071828","https://openalex.org/W4390873054","https://openalex.org/W4393160294","https://openalex.org/W4401809402","https://openalex.org/W4403363072","https://openalex.org/W4403674737","https://openalex.org/W4411245083","https://openalex.org/W6739901393","https://openalex.org/W6779823529","https://openalex.org/W6791353385","https://openalex.org/W6849109464","https://openalex.org/W6854445938","https://openalex.org/W6855771293","https://openalex.org/W6868818234","https://openalex.org/W6869582388","https://openalex.org/W6875493355"],"related_works":["https://openalex.org/W2523036031","https://openalex.org/W4237383858","https://openalex.org/W3211743321","https://openalex.org/W2016968289","https://openalex.org/W2021759681","https://openalex.org/W2011071567","https://openalex.org/W4256291417","https://openalex.org/W2059053411","https://openalex.org/W4248667156","https://openalex.org/W2006304570"],"abstract_inverted_index":{"The":[0,56,134],"video-to-audio":[1],"(V2A)":[2],"generation":[3,29,90,108],"task":[4],"has":[5],"drawn":[6],"attention":[7],"in":[8,17,98],"the":[9,15,28,68,85,89,173],"field":[10],"of":[11,128,136],"multimedia":[12],"due":[13],"to":[14,27,31,91,104,184],"practicality":[16],"producing":[18],"Foley":[19],"sound.":[20],"Semantic":[21],"and":[22,35,43,95,131,150,167,181],"temporal":[23,36,57,96,120,123],"conditions":[24,124],"are":[25,46,102],"fed":[26],"model":[30,80],"indicate":[32],"sound":[33,165],"events":[34],"occurrence.":[37],"Recent":[38],"studies":[39],"on":[40,50,162],"synthesizing":[41],"immersive":[42],"synchronized":[44],"audio":[45,174],"faced":[47],"with":[48,52],"challenges":[49],"videos":[51],"moving":[53],"visual":[54,129],"presence.":[55],"condition":[58,66],"is":[59],"not":[60],"accurate":[61],"enough":[62],"while":[63,118],"low-resolution":[64],"semantic":[65,82,94,137,171],"exacerbates":[67],"problem.":[69],"To":[70],"tackle":[71],"these":[72],"challenges,":[73],"we":[74],"propose":[75],"Smooth-Foley,":[76],"a":[77,119],"V2A":[78],"generative":[79],"taking":[81],"guidance":[83,138],"from":[84,126,139],"textual":[86,132,140],"label":[87],"across":[88],"enhance":[92],"both":[93,163],"alignment":[97],"audio.":[99],"Two":[100],"adapters":[101],"trained":[103],"leverage":[105],"pre-trained":[106],"text-to-audio":[107],"models.":[109],"A":[110],"frame":[111],"adapter":[112,121],"integrates":[113,122],"high-resolution":[114],"frame-wise":[115],"video":[116],"features":[117],"obtained":[125],"similarities":[127],"frames":[130],"labels.":[133],"incorporation":[135],"labels":[141],"achieves":[142],"precise":[143],"audio-video":[144],"alignment.":[145],"We":[146],"conduct":[147],"extensive":[148],"quantitative":[149],"qualitative":[151],"experiments.":[152],"Results":[153],"show":[154],"that":[155],"Smooth-Foley":[156,177],"performs":[157],"better":[158,182],"than":[159],"existing":[160],"models":[161],"continuous":[164],"scenarios":[166],"general":[168],"scenarios.":[169],"With":[170],"guidance,":[172],"generated":[175],"by":[176],"exhibits":[178],"higher":[179],"quality":[180],"adherence":[183],"physical":[185],"laws.":[186],"Homepage:":[187],"https://danny-c-auditore.github.io/smoothfoley.github.io/":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}