{"id":"https://openalex.org/W4392910528","doi":"https://doi.org/10.1109/icassp48485.2024.10447063","title":"Syncfusion: Multimodal Onset-Synchronized Video-to-Audio Foley Synthesis","display_name":"Syncfusion: Multimodal Onset-Synchronized Video-to-Audio Foley Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910528","doi":"https://doi.org/10.1109/icassp48485.2024.10447063"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5045230175","display_name":"Marco Comunit\u00e0","orcid":"https://orcid.org/0000-0001-8097-9877"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Marco Comunit\u00e0","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK","Centre for Digital Music, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046834719","display_name":"Riccardo Fosco Gramaccioni","orcid":"https://orcid.org/0009-0003-1398-1880"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo F. Gramaccioni","raw_affiliation_strings":["Sapienza University of Rome,Italy","Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069620223","display_name":"Emilian Postolache","orcid":"https://orcid.org/0000-0002-4785-5204"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emilian Postolache","raw_affiliation_strings":["Sapienza University of Rome,Italy","Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087051832","display_name":"Emanuele Rodol\u00e0","orcid":"https://orcid.org/0000-0003-0091-7241"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Rodol\u00e0","raw_affiliation_strings":["Sapienza University of Rome,Italy","Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019647783","display_name":"Danilo Comminiello","orcid":"https://orcid.org/0000-0003-4067-4504"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danilo Comminiello","raw_affiliation_strings":["Sapienza University of Rome,Italy","Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111403298","display_name":"Joshua D. Reiss","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joshua D. Reiss","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK","Centre for Digital Music, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045230175"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":4.6956,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95605329,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"936","last_page":"940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9868999719619751,"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/T10860","display_name":"Speech and Audio Processing","score":0.9868999719619751,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9560999870300293,"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/T13905","display_name":"Telecommunications and Broadcasting Technologies","score":0.9059000015258789,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7210633754730225},{"id":"https://openalex.org/keywords/foley","display_name":"Foley","score":0.631831705570221},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3812796473503113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210633754730225},{"id":"https://openalex.org/C110446960","wikidata":"https://www.wikidata.org/wiki/Q762316","display_name":"Foley","level":2,"score":0.631831705570221},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3812796473503113},{"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":3,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1725167","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1725167","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97982","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97982","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2009895621","display_name":"UKRI Centre for Doctoral Training in Artificial Intelligence and Music","funder_award_id":"EP/S022694/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5356239126","display_name":null,"funder_award_id":"CN00000013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6605893610","display_name":"Spectral geometric methods in practice","funder_award_id":"802554","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8793594538","display_name":null,"funder_award_id":"EP/S022694/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W2012210378","https://openalex.org/W2560662850","https://openalex.org/W2775795276","https://openalex.org/W2964345931","https://openalex.org/W2993657948","https://openalex.org/W3034527633","https://openalex.org/W3162391496","https://openalex.org/W3176411119","https://openalex.org/W3187009280","https://openalex.org/W3201143670","https://openalex.org/W4289106098","https://openalex.org/W4297841713","https://openalex.org/W4308663722","https://openalex.org/W4319452539","https://openalex.org/W4327810154","https://openalex.org/W4372263438","https://openalex.org/W4372266552","https://openalex.org/W4383045354","https://openalex.org/W4386071656","https://openalex.org/W4386071828","https://openalex.org/W4393160294","https://openalex.org/W6747218270","https://openalex.org/W6757220786","https://openalex.org/W6767111847","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6802805937","https://openalex.org/W6809884996","https://openalex.org/W6810980340","https://openalex.org/W6840815571","https://openalex.org/W6845298728","https://openalex.org/W6848854281","https://openalex.org/W6850985150","https://openalex.org/W6854445938"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Sound":[0],"design":[1],"involves":[2],"creatively":[3],"selecting,":[4],"recording,":[5],"and":[6,17,54,159],"editing":[7,130,144],"sound":[8,28,105,119,155],"effects":[9,106],"for":[10],"various":[11],"media":[12],"like":[13],"cinema,":[14],"video":[15,40,52],"games,":[16],"virtual/augmented":[18],"reality.":[19],"One":[20],"of":[21,63,125],"the":[22,48,67,118,123,131,136,145,150],"most":[23],"time-consuming":[24],"steps":[25],"when":[26],"designing":[27],"is":[29],"synchronizing":[30],"audio":[31,58,89,107,146],"with":[32,88,127],"video.":[33,68,128],"In":[34,109],"some":[35],"cases,":[36],"environmental":[37],"recordings":[38],"from":[39,66,78],"shoots":[41],"are":[42,82],"available,":[43],"which":[44,81],"can":[45],"aid":[46],"in":[47,51,86],"process.":[49,152],"However,":[50],"games":[53],"animations,":[55],"no":[56],"reference":[57],"exists,":[59],"requiring":[60],"manual":[61],"annotation":[62],"event":[64],"timings":[65],"We":[69,153],"propose":[70],"a":[71,79,96,102],"system":[72],"to":[73,94,100,117,162],"extract":[74],"repetitive":[75],"actions":[76],"onsets":[77],"video,":[80],"then":[83],"used":[84],"-":[85,93],"conjunction":[87],"or":[90,134],"textual":[91],"embeddings":[92],"condition":[95],"diffusion":[97],"model":[98],"trained":[99],"generate":[101],"new":[103],"synchronized":[104],"track.":[108],"this":[110],"way,":[111],"we":[112],"leave":[113],"complete":[114],"creative":[115],"control":[116],"designer":[120],"while":[121],"removing":[122],"burden":[124],"synchronization":[126],"Furthermore,":[129],"onset":[132],"track":[133,147],"changing":[135],"conditioning":[137],"embedding":[138],"requires":[139],"much":[140],"less":[141],"effort":[142],"than":[143],"itself,":[148],"simplifying":[149],"sonification":[151],"provide":[154],"examples,":[156],"source":[157],"code,":[158],"pretrained":[160],"models":[161],"faciliate":[163],"reproducibility":[164],"<sup":[165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[167],".":[168]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12}],"updated_date":"2026-05-25T08:39:21.599409","created_date":"2025-10-10T00:00:00"}
