{"id":"https://openalex.org/W7105657759","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229067","title":"FoleyGRAM: Video-to-Audio Generation with GRAM-Aligned Multimodal Encoders","display_name":"FoleyGRAM: Video-to-Audio Generation with GRAM-Aligned Multimodal Encoders","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105657759","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229067"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":null,"display_name":"Riccardo F. Gramaccioni","orcid":null},"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":true,"raw_author_name":"Riccardo F. Gramaccioni","raw_affiliation_strings":["Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christian Marinoni","orcid":null},"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":"Christian Marinoni","raw_affiliation_strings":["Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Eleonora Grassucci","orcid":null},"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":"Eleonora Grassucci","raw_affiliation_strings":["Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Giordano Cicchetti","orcid":null},"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":"Giordano Cicchetti","raw_affiliation_strings":["Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aurelio Uncini","orcid":null},"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":"Aurelio Uncini","raw_affiliation_strings":["Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":null,"display_name":"Danilo Comminiello","orcid":null},"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,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. Information Engineering, Electronics and Telecommunications (DIET),Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5773951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.815500020980835,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.815500020980835,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.057500001043081284,"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":0.012900000438094139,"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/encoder","display_name":"Encoder","score":0.7010999917984009},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.511900007724762},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.46470001339912415},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44839999079704285},{"id":"https://openalex.org/keywords/gramian-matrix","display_name":"Gramian matrix","score":0.4262999892234802},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.39100000262260437},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3709000051021576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7010999917984009},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49390000104904175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46970000863075256},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44839999079704285},{"id":"https://openalex.org/C77246614","wikidata":"https://www.wikidata.org/wiki/Q1409400","display_name":"Gramian matrix","level":3,"score":0.4262999892234802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.39100000262260437},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C516976414","wikidata":"https://www.wikidata.org/wiki/Q1606582","display_name":"Nasalization","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":23,"referenced_works":["https://openalex.org/W2526050071","https://openalex.org/W2963524571","https://openalex.org/W2963807156","https://openalex.org/W2964345931","https://openalex.org/W2972478942","https://openalex.org/W3046890131","https://openalex.org/W3187009280","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4372348103","https://openalex.org/W4375868912","https://openalex.org/W4382318654","https://openalex.org/W4386071707","https://openalex.org/W4386071828","https://openalex.org/W4392903391","https://openalex.org/W4392910528","https://openalex.org/W4398226295","https://openalex.org/W4403363072","https://openalex.org/W4403990379","https://openalex.org/W4408345930","https://openalex.org/W4411245083","https://openalex.org/W4413462963","https://openalex.org/W7103756088"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"present":[4],"FoleyGRAM,":[5],"a":[6,61,93],"novel":[7],"approach":[8],"to":[9,38,112],"video-to-audio":[10,28,97,127],"generation":[11,54],"that":[12,102],"emphasizes":[13],"semantic":[14,49,75],"conditioning":[15],"through":[16],"the":[17,32,52,81,89,109,121,124],"use":[18],"of":[19,58,123],"aligned":[20],"multimodal":[21,104],"encoders.":[22],"Building":[23],"on":[24,67,88],"prior":[25],"advancements":[26],"in":[27,126],"generation,":[29],"FoleyGRAM":[30,59,87],"leverages":[31],"Gramian":[33],"Representation":[34],"Alignment":[35],"Measure":[36],"(GRAM)":[37],"align":[39,114],"embeddings":[40,69],"across":[41],"video,":[42],"text,":[43],"and":[44,70,77],"audio":[45,53,63,116],"modalities,":[46],"enabling":[47],"precise":[48],"control":[50],"over":[51],"process.":[55],"The":[56],"core":[57],"is":[60],"diffusion-based":[62],"synthesis":[64],"model":[65],"conditioned":[66],"GRAM-aligned":[68],"waveform":[71],"envelopes,":[72],"ensuring":[73],"both":[74],"richness":[76],"temporal":[78],"alignment":[79],"with":[80,117],"corresponding":[82],"input":[83],"video.":[84],"We":[85],"evaluate":[86],"Greatest":[90],"Hits":[91],"dataset,":[92],"standard":[94],"benchmark":[95],"for":[96],"models.":[98],"Our":[99],"experiments":[100],"demonstrate":[101],"aligning":[103],"encoders":[105],"using":[106],"GRAM":[107],"enhances":[108],"system\u2019s":[110],"ability":[111],"semantically":[113],"generated":[115],"video":[118],"content,":[119],"advancing":[120],"state":[122],"art":[125],"synthesis.":[128]},"counts_by_year":[],"updated_date":"2025-11-15T23:13:30.683059","created_date":"2025-11-14T00:00:00"}