{"id":"https://openalex.org/W4408353444","doi":"https://doi.org/10.1109/icassp49660.2025.10888189","title":"Rhythmic Foley: A Framework For Seamless Audio-Visual Alignment In Video-to-Audio Synthesis","display_name":"Rhythmic Foley: A Framework For Seamless Audio-Visual Alignment In Video-to-Audio Synthesis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353444","doi":"https://doi.org/10.1109/icassp49660.2025.10888189"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888189","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":"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":"https://openalex.org/A5057231069","display_name":"Zhiqi Huang","orcid":"https://orcid.org/0000-0002-5749-9573"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Huang","raw_affiliation_strings":["Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101447211","display_name":"Dan Luo","orcid":"https://orcid.org/0000-0002-7526-9261"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Luo","raw_affiliation_strings":["Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695510","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-7437-8503"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083413053","display_name":"Huan Liao","orcid":"https://orcid.org/0009-0006-9895-7995"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Liao","raw_affiliation_strings":["Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100765836","display_name":"Zhiheng Li","orcid":"https://orcid.org/0000-0002-1477-2066"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Li","raw_affiliation_strings":["Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062684618","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-6374-6617"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9541000127792358,"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":0.9541000127792358,"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":0.9320999979972839,"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":0.7935653328895569},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6494513750076294},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.5835832357406616},{"id":"https://openalex.org/keywords/foley","display_name":"Foley","score":0.4935184717178345},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44093799591064453},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.43704479932785034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43425488471984863},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3003169894218445},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.22637969255447388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935653328895569},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6494513750076294},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.5835832357406616},{"id":"https://openalex.org/C110446960","wikidata":"https://www.wikidata.org/wiki/Q762316","display_name":"Foley","level":2,"score":0.4935184717178345},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44093799591064453},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.43704479932785034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43425488471984863},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3003169894218445},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.22637969255447388},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888189","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":[{"score":0.5699999928474426,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2191779130","https://openalex.org/W2302255633","https://openalex.org/W2593116425","https://openalex.org/W3015371781","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4381786045","https://openalex.org/W4386071828","https://openalex.org/W4387969125","https://openalex.org/W4390873054","https://openalex.org/W4392909615","https://openalex.org/W4393160294","https://openalex.org/W4396877837","https://openalex.org/W4401024632","https://openalex.org/W4402727849","https://openalex.org/W4402816831","https://openalex.org/W4402955558","https://openalex.org/W4403780831","https://openalex.org/W4404439850","https://openalex.org/W4411245083","https://openalex.org/W6765779288","https://openalex.org/W6791353385","https://openalex.org/W6849109464","https://openalex.org/W6851950068","https://openalex.org/W6854445938","https://openalex.org/W6857872576","https://openalex.org/W6859304583","https://openalex.org/W6859583170","https://openalex.org/W6862974260","https://openalex.org/W6865466262","https://openalex.org/W6869509520","https://openalex.org/W6869582388","https://openalex.org/W6870183580","https://openalex.org/W6870339939","https://openalex.org/W6870515680"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686","https://openalex.org/W2371215329","https://openalex.org/W1975359510"],"abstract_inverted_index":{"Our":[0],"research":[1],"introduces":[2],"an":[3],"innovative":[4],"framework":[5,105],"for":[6],"video-to-audio":[7],"synthesis,":[8],"which":[9],"solves":[10],"the":[11,20,40,68,71,89,92,101],"problems":[12],"of":[13,42,70,91,103],"audio-video":[14],"desynchronization":[15],"and":[16,28,39,63,85],"semantic":[17,25,37],"loss":[18],"in":[19,47,106],"audio.":[21,73],"By":[22],"incorporating":[23],"a":[24,29,52],"alignment":[26],"adapter":[27],"temporal":[30],"synchronization":[31],"adapter,":[32],"our":[33,57,104],"method":[34],"significantly":[35],"improves":[36],"integrity":[38],"precision":[41],"beat":[43,86],"point":[44],"synchronization,":[45],"particularly":[46],"fast-paced":[48],"action":[49],"sequences.":[50],"Utilizing":[51],"contrastive":[53],"audio-visual":[54,109],"pre-trained":[55],"encoder,":[56],"model":[58],"is":[59],"trained":[60],"with":[61,79],"video":[62],"high-quality":[64],"audio":[65,83],"data,":[66],"improving":[67],"quality":[69],"generated":[72],"This":[74],"dual-adapter":[75],"approach":[76],"empowers":[77],"users":[78],"enhanced":[80],"control":[81],"over":[82],"semantics":[84],"effects,":[87],"allowing":[88],"adjustment":[90],"controller":[93],"to":[94],"achieve":[95],"better":[96],"results.":[97],"Extensive":[98],"experiments":[99],"substantiate":[100],"effectiveness":[102],"achieving":[107],"seamless":[108],"alignment.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}