{"id":"https://openalex.org/W4327521813","doi":"https://doi.org/10.1109/access.2023.3257565","title":"Audio-to-Visual Cross-Modal Generation of Birds","display_name":"Audio-to-Visual Cross-Modal Generation of Birds","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4327521813","doi":"https://doi.org/10.1109/access.2023.3257565"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3257565","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3257565","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10070771.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10070771.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112651903","display_name":"Joo Yong Shim","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joo Yong Shim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049202871","display_name":"Joongheon Kim","orcid":"https://orcid.org/0000-0003-2126-768X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joongheon Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-2126-768X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018364461","display_name":"Jong\u2010Kook Kim","orcid":"https://orcid.org/0000-0003-1828-7807"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong-Kook Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-1828-7807","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.5657,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83445837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"27719","last_page":"27729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9732999801635742,"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":0.8483725786209106},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7027095556259155},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6323830485343933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5982544422149658},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5171184539794922},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4939466118812561},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4811604917049408},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4799118936061859},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46842774748802185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4571435749530792},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45258814096450806},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37513625621795654},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09147682785987854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483725786209106},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7027095556259155},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6323830485343933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5982544422149658},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5171184539794922},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4939466118812561},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4811604917049408},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4799118936061859},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46842774748802185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4571435749530792},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45258814096450806},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37513625621795654},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09147682785987854},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3257565","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3257565","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10070771.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0d0de150a247434c895f66b380ff0e89","is_oa":true,"landing_page_url":"https://doaj.org/article/0d0de150a247434c895f66b380ff0e89","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 27719-27729 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3257565","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3257565","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10070771.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4734719780","display_name":null,"funder_award_id":"NRF-2016R1D1A1B04933156","funder_id":"https://openalex.org/F4320311687","funder_display_name":"Ministry of Education"},{"id":"https://openalex.org/G7066427888","display_name":null,"funder_award_id":"NRF-2016R1D1A1B04933156","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4327521813.pdf","grobid_xml":"https://content.openalex.org/works/W4327521813.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1523802035","https://openalex.org/W1797268635","https://openalex.org/W2065274193","https://openalex.org/W2069943693","https://openalex.org/W2073546306","https://openalex.org/W2125389028","https://openalex.org/W2183341477","https://openalex.org/W2187089797","https://openalex.org/W2340600463","https://openalex.org/W2474574787","https://openalex.org/W2564325886","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2759171953","https://openalex.org/W2784500888","https://openalex.org/W2802101759","https://openalex.org/W2951611190","https://openalex.org/W2963066677","https://openalex.org/W2963115079","https://openalex.org/W2963163163","https://openalex.org/W2963663420","https://openalex.org/W2963684088","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2981087920","https://openalex.org/W2994125460","https://openalex.org/W3005881764","https://openalex.org/W3007605881","https://openalex.org/W3017939645","https://openalex.org/W3087576944","https://openalex.org/W3101943858","https://openalex.org/W3105017218","https://openalex.org/W3118548710","https://openalex.org/W3154807520","https://openalex.org/W3160431667","https://openalex.org/W3162846947","https://openalex.org/W3173223111","https://openalex.org/W6637373629","https://openalex.org/W6638319203","https://openalex.org/W6678815747","https://openalex.org/W6685352114","https://openalex.org/W6718379498","https://openalex.org/W6729482032","https://openalex.org/W6729831399","https://openalex.org/W6743796535","https://openalex.org/W6765779288","https://openalex.org/W6766864773","https://openalex.org/W6791026367"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"Audio":[0],"and":[1,61,81,87,93,115,135],"visual":[2,20,32],"modal":[3],"data":[4,21,24,33,36,60],"are":[5],"essential":[6],"elements":[7],"of":[8,57,118],"precise":[9],"investigation":[10],"in":[11],"many":[12],"fields.":[13],"Sometimes":[14],"it":[15],"is":[16,25,73,99],"difficult":[17],"to":[18,75,90],"obtain":[19],"while":[22],"auditory":[23,59],"easily":[26],"available.":[27],"In":[28],"this":[29,102],"case,":[30],"generating":[31],"using":[34,67],"audio":[35,69,88],"will":[37],"be":[38],"very":[39],"helpful.":[40],"This":[41,71],"paper":[42],"proposes":[43],"a":[44,62],"novel":[45],"audio-to-visual":[46],"cross-modal":[47],"generation":[48],"approach.":[49],"The":[50,123],"proposed":[51,129],"sound":[52],"encoder":[53],"extracts":[54],"the":[55,58,105,113,128,141],"features":[56],"generative":[63],"model":[64,72],"generates":[65],"images":[66,86,117,134],"those":[68],"features.":[70],"expected":[74],"learn":[76],"(i)":[77],"valid":[78],"feature":[79],"representation":[80],"(ii)":[82],"associations":[83],"between":[84],"generated":[85],"inputs":[89],"generate":[91,132],"realistic":[92],"well-classified":[94],"images.":[95],"A":[96],"new":[97],"dataset":[98,110],"collected":[100],"for":[101],"research":[103],"called":[104],"Audio-Visual":[106],"Corresponding":[107],"Bird":[108],"(AVC-B)":[109],"which":[111],"contains":[112],"sounds":[114],"corresponding":[116],"10":[119],"different":[120],"bird":[121],"species.":[122],"experimental":[124],"results":[125,139],"show":[126],"that":[127],"method":[130],"can":[131],"class-appropriate":[133],"achieve":[136],"better":[137],"classification":[138],"than":[140],"state-of-the-art":[142],"methods.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
