{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:38:07Z","timestamp":1775068687389,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["22H03612"],"award-info":[{"award-number":["22H03612"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Microsoft Research CORE16 program"},{"name":"Nagoya University Interdisciplinary Frontier Fellowship??","award":["JPMJFS2120"],"award-info":[{"award-number":["JPMJFS2120"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3378095","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T19:21:25Z","timestamp":1710789685000},"page":"41299-41316","source":"Crossref","is-referenced-by-count":5,"title":["Interpolating the Text-to-Image Correspondence Based on Phonetic and Phonological Similarities for Nonword-to-Image Generation"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2453-4560","authenticated-orcid":false,"given":"Chihaya","family":"Matsuhira","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-5973","authenticated-orcid":false,"given":"Marc A.","family":"Kastner","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3041-4330","authenticated-orcid":false,"given":"Takahiro","family":"Komamizu","sequence":"additional","affiliation":[{"name":"Mathematical and Data Science Center, Nagoya University, Nagoya, Aichi, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6290-9680","authenticated-orcid":false,"given":"Takatsugu","family":"Hirayama","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6040-4988","authenticated-orcid":false,"given":"Keisuke","family":"Doman","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3799-4550","authenticated-orcid":false,"given":"Yasutomo","family":"Kawanishi","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3942-9296","authenticated-orcid":false,"given":"Ichiro","family":"Ide","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"arXiv:2102.12092"},{"key":"ref2","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref3","volume-title":"Improving Image Generation With Better Captions","author":"Betker","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","volume-title":"Stable Diffusion","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584078"},{"key":"ref7","first-page":"1","article-title":"Discovering the hidden vocabulary of DALLE-2","volume-title":"Proc. Workshop Score-Based Methods","author":"Daras"},{"key":"ref8","article-title":"Adversarial attacks on image generation with made-up words","author":"Milli\u00e8re","year":"2022","journal-title":"arXiv:2208.04135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00236"},{"key":"ref10","article-title":"IPA-CLIP: Integrating phonetic priors into vision and language pretraining","author":"Matsuhira","year":"2023","journal-title":"arXiv:2303.03144"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3607541.3616818"},{"issue":"2","key":"ref12","first-page":"23","article-title":"A new algorithm for data compression","volume":"12","author":"Gage","year":"1994","journal-title":"C Users J."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.wassa-1.4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511751806"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2307\/417209"},{"key":"ref18","volume-title":"Gestalt Psychology","author":"K\u00f6hler","year":"1929"},{"issue":"12","key":"ref19","first-page":"3","article-title":"Synaesthesia\u2014A window into perception, thought and language","volume":"8","author":"Ramachandran","year":"2001","journal-title":"J. Conscious. Stud."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-7687.2006.00495.x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jecp.2012.05.004"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.18.6.1211"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2018.02.007"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref26","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref27","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"key":"ref28","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv:2205.11487"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref30","first-page":"6848","article-title":"Cross-lingual and multilingual CLIP","volume-title":"Proc. 13th Lang. Resour. Eval. Conf.","author":"Carlsson"},{"key":"ref31","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"issue":"1","key":"ref36","first-page":"136","article-title":"Sound analogies with phoneme embeddings","volume":"1","author":"Silfverberg","year":"2018","journal-title":"Proc. Soc. Comput. Linguist."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4219"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.470"},{"key":"ref39","volume-title":"Learning Multiple Layers of Features From Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1080\/02724980244000099"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00028"},{"key":"ref42","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NIPS","author":"Heusel"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01592"},{"key":"ref45","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Kingma"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10473073.pdf?arnumber=10473073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T21:29:56Z","timestamp":1711488596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10473073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3378095","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}