{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T05:34:39Z","timestamp":1773552879656,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Basic Science Research Program"},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","award":["NRF-2016R1D1A1B04933156"],"award-info":[{"award-number":["NRF-2016R1D1A1B04933156"]}],"id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3257565","type":"journal-article","created":{"date-parts":[[2023,3,15]],"date-time":"2023-03-15T17:45:38Z","timestamp":1678902338000},"page":"27719-27729","source":"Crossref","is-referenced-by-count":9,"title":["Audio-to-Visual Cross-Modal Generation of Birds"],"prefix":"10.1109","volume":"11","author":[{"given":"Joo Yong","family":"Shim","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2126-768X","authenticated-orcid":false,"given":"Joongheon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1828-7807","authenticated-orcid":false,"given":"Jong-Kook","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2557722"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050089"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.321"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref7","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015","journal-title":"arXiv:1511.06434"},{"key":"ref8","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv:1411.1784"},{"key":"ref9","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier GANs","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Odena"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2834866"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2229969"},{"key":"ref15","first-page":"1","article-title":"Large-scale bird sound classification using convolutional neural networks","volume-title":"Proc. Working Notes CLEF Conf. Labs Eval. Forum","volume":"1866","author":"Kahl"},{"issue":"2380","key":"ref16","first-page":"1","article-title":"Overview of BirdCLEF 2019: Large-scale bird recognition in soundscapes","volume-title":"Proc. Working Notes CLEF Conf. Labs Eval. Forum","author":"Kahl"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.488"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2957572"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/AISP48273.2020.9073584"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/bij.12455"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/evo.14099"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12329"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412890"},{"key":"ref28","first-page":"1188","article-title":"Diverse audio-to-image generation via semantics and feature consistency","volume-title":"Proc. Asia\u2013Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Yang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682383"},{"key":"ref30","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref31","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2646180"},{"key":"ref33","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"29","author":"Aytar"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2794780"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2228476"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3005033"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412721"},{"key":"ref41","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref42","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref43","volume-title":"Xeno-Canto:: Sharing Bird Sounds From Around the World","author":"Planqu\u00e9","year":"2022"},{"key":"ref44","volume-title":"LLLNet","author":"Kajihara","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref46","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10070771.pdf?arnumber=10070771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:31:06Z","timestamp":1707831066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10070771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3257565","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}