{"id":"https://openalex.org/W3162846947","doi":"https://doi.org/10.1109/icpr48806.2021.9412721","title":"S2I-Bird: Sound-to-Image Generation of Bird Species using Generative Adversarial Networks","display_name":"S2I-Bird: Sound-to-Image Generation of Bird Species using Generative Adversarial Networks","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3162846947","doi":"https://doi.org/10.1109/icpr48806.2021.9412721","mag":"3162846947"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/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":true,"raw_author_name":"Joo Yong Shim","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical 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":["School of Electrical Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical 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":["School of Electrical Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112651903"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":1.0665,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76315078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2226","last_page":"2232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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":0.9958000183105469,"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":0.9940999746322632,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.980400025844574,"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/computer-science","display_name":"Computer science","score":0.734424889087677},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7259817123413086},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6057122349739075},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6019761562347412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5948668718338013},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5539634227752686},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5359082818031311},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5138257145881653},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.507274329662323},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4912523627281189},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.437500536441803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41482752561569214},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10740527510643005},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08703413605690002},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08165735006332397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734424889087677},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7259817123413086},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6057122349739075},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6019761562347412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5948668718338013},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5539634227752686},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5359082818031311},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5138257145881653},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.507274329662323},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4912523627281189},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.437500536441803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41482752561569214},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10740527510643005},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08703413605690002},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08165735006332397},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G569278201","display_name":null,"funder_award_id":"NRF-2016R1D1A1B04933156","funder_id":"https://openalex.org/F4320311039","funder_display_name":"Ministry of Higher Education and Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320311039","display_name":"Ministry of Higher Education and Scientific Research","ror":"https://ror.org/00kab6t91"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1523802035","https://openalex.org/W1686810756","https://openalex.org/W1797268635","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2183341477","https://openalex.org/W2576656823","https://openalex.org/W2619697695","https://openalex.org/W2759171953","https://openalex.org/W2929648250","https://openalex.org/W2950776302","https://openalex.org/W2951611190","https://openalex.org/W2962756039","https://openalex.org/W2962835968","https://openalex.org/W2963115079","https://openalex.org/W2963163163","https://openalex.org/W2963373786","https://openalex.org/W2963663420","https://openalex.org/W2963684088","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W4293665662","https://openalex.org/W4320013936","https://openalex.org/W6637373629","https://openalex.org/W6718379498","https://openalex.org/W6729482032","https://openalex.org/W6729831399","https://openalex.org/W6732407650","https://openalex.org/W6745983426","https://openalex.org/W6747045456","https://openalex.org/W6761232514","https://openalex.org/W6943624720"],"related_works":["https://openalex.org/W4220812973","https://openalex.org/W3198184493","https://openalex.org/W3156291593","https://openalex.org/W2901368259","https://openalex.org/W2973444776","https://openalex.org/W4283579220","https://openalex.org/W3195755139","https://openalex.org/W4312525628","https://openalex.org/W4206598283","https://openalex.org/W3049517484"],"abstract_inverted_index":{"Generating":[0],"images":[1,19,47],"from":[2,20,39],"sound":[3,23,30],"is":[4],"a":[5,11,29,78],"challenging":[6],"task.":[7],"This":[8],"paper":[9],"proposes":[10],"novel":[12],"deep":[13],"learning":[14],"model":[15,27,66],"that":[16,48,64],"generates":[17,45],"bird":[18,46],"their":[21],"corresponding":[22],"information.":[24],"Our":[25],"proposed":[26],"includes":[28],"encoder":[31],"in":[32,77],"order":[33],"to":[34,50],"extract":[35],"suitable":[36],"feature":[37],"representations":[38],"audio":[40],"recordings,":[41],"and":[42],"then":[43],"it":[44],"corresponds":[49],"its":[51],"calls":[52],"using":[53],"conditional":[54],"generative":[55],"adversarial":[56],"networks":[57],"(cGANs)":[58],"with":[59],"auxiliary":[60],"classifiers.":[61],"We":[62],"demonstrate":[63],"our":[65],"produces":[67],"better":[68],"image":[69],"generation":[70],"results":[71],"which":[72],"outperforms":[73],"other":[74],"state-of-the-art":[75],"methods":[76],"similar":[79],"context.":[80]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
