{"id":"https://openalex.org/W4415272450","doi":"https://doi.org/10.1145/3743093.3770976","title":"SeeingSounds: Learning Audio-to-Visual Alignment via Text","display_name":"SeeingSounds: Learning Audio-to-Visual Alignment via Text","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4415272450","doi":"https://doi.org/10.1145/3743093.3770976"},"language":"en","primary_location":{"id":"doi:10.1145/3743093.3770976","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770976","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770976","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770976","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114730056","display_name":"Simone Carnemolla","orcid":"https://orcid.org/0009-0005-8367-3933"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Simone Carnemolla","raw_affiliation_strings":["University of Catania, Catania, Italy"],"raw_orcid":"https://orcid.org/0009-0005-8367-3933","affiliations":[{"raw_affiliation_string":"University of Catania, Catania, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003973109","display_name":"Matteo Pennisi","orcid":"https://orcid.org/0000-0002-6721-4383"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Pennisi","raw_affiliation_strings":["University of Catania, Catania, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6721-4383","affiliations":[{"raw_affiliation_string":"University of Catania, Catania, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091250843","display_name":"Chiara Russo","orcid":null},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Chiara Maria Russo","raw_affiliation_strings":["University of Catania, Catania, Italy"],"raw_orcid":"https://orcid.org/0009-0006-4402-6159","affiliations":[{"raw_affiliation_string":"University of Catania, Catania, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031450889","display_name":"Simone Palazzo","orcid":"https://orcid.org/0000-0002-2441-0982"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Palazzo","raw_affiliation_strings":["University of Catania, Catania, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2441-0982","affiliations":[{"raw_affiliation_string":"University of Catania, Catania, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101841330","display_name":"Daniela Giordano","orcid":"https://orcid.org/0000-0001-5135-1351"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniela Giordano","raw_affiliation_strings":["University of Catania, Catania, Italy"],"raw_orcid":"https://orcid.org/0000-0001-5135-1351","affiliations":[{"raw_affiliation_string":"University of Catania, Catania, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075815307","display_name":"Concetto Spampinato","orcid":null},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Concetto Spampinato","raw_affiliation_strings":["University of Catania, Catania, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6653-2577","affiliations":[{"raw_affiliation_string":"University of Catania, Catania, Italy","institution_ids":["https://openalex.org/I39063666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114730056"],"corresponding_institution_ids":["https://openalex.org/I39063666"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34398198,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9897000193595886,"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":0.9897000193595886,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9629999995231628,"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/generative-grammar","display_name":"Generative grammar","score":0.4830000102519989},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.48019999265670776},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47510001063346863},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46459999680519104},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44850000739097595},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4194999933242798},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3671000003814697},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.3262999951839447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961000204086304},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5403000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123999714851379},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4194999933242798},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3330000042915344},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3743093.3770976","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770976","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770976","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.11738","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.11738","pdf_url":"https://arxiv.org/pdf/2510.11738","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"}],"best_oa_location":{"id":"doi:10.1145/3743093.3770976","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770976","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770976","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1735496595","display_name":null,"funder_award_id":"E63C22001940006","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415272450.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"SeeingSounds,":[2],"a":[3,36,55,60,72,157],"lightweight":[4,100],"and":[5,18,97,104,111,153],"modular":[6],"framework":[7],"for":[8,38],"audio-to-image":[9],"generation":[10],"that":[11,135,145],"leverages":[12],"the":[13,68,82,161],"interplay":[14],"between":[15],"audio,":[16],"language,":[17],"vision\u2014without":[19],"requiring":[20],"any":[21],"paired":[22],"audio-visual":[23],"data":[24],"or":[25,40,124],"training":[26],"on":[27,43,93],"visual":[28,69,137],"generative":[29],"models.":[30],"Rather":[31],"than":[32],"treating":[33],"audio":[34,51,120],"as":[35],"substitute":[37],"text":[39,116],"relying":[41],"solely":[42],"audio-to-text":[44],"mappings,":[45],"our":[46],"method":[47],"performs":[48],"dual":[49],"alignment:":[50],"is":[52],"projected":[53],"into":[54,67,128],"semantic":[56],"language":[57,62],"space":[58],"via":[59],"frozen":[61,94],"encoder,":[63],"and,":[64],"contextually":[65],"grounded":[66],"domain":[70],"using":[71],"vision-language":[73],"model.":[74],"This":[75],"approach,":[76],"inspired":[77],"by":[78],"cognitive":[79],"neuroscience,":[80],"reflects":[81],"natural":[83],"cross-modal":[84],"associations":[85],"observed":[86],"in":[87,150,163],"human":[88],"perception.":[89],"The":[90],"model":[91],"operates":[92],"diffusion":[95],"backbones":[96],"trains":[98],"only":[99],"adapters,":[101],"enabling":[102],"efficient":[103],"scalable":[105],"learning.":[106],"Moreover,":[107],"it":[108],"supports":[109],"fine-grained":[110],"interpretable":[112],"control":[113],"through":[114],"procedural":[115],"prompt":[117],"generation,":[118],"where":[119],"transformations":[121],"(e.g.,":[122,131],"volume":[123],"pitch":[125],"shifts)":[126],"translate":[127],"descriptive":[129],"prompts":[130],"\u201ca":[132],"distant":[133],"thunder\u201d)":[134],"guide":[136],"outputs.":[138],"Extensive":[139],"experiments":[140],"across":[141],"standard":[142],"benchmarks":[143],"confirm":[144],"SeeingSounds":[146],"outperforms":[147],"existing":[148],"methods":[149],"both":[151],"zero-shot":[152],"supervised":[154],"settings,":[155],"establishing":[156],"new":[158],"state":[159],"of":[160],"art":[162],"controllable":[164],"audio-to-visual":[165],"generation.":[166]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-17T00:00:00"}