{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:19Z","timestamp":1740169219488,"version":"3.37.3"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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 (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["JP17H06101","JP21H03467"],"award-info":[{"award-number":["JP17H06101","JP21H03467"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google AI Focused Research Awards Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3077886","type":"journal-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T19:50:40Z","timestamp":1620330640000},"page":"70286-70299","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal Chain: Cross-Modal Collaboration Through Listening, Speaking, and Visualizing"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-415X","authenticated-orcid":false,"given":"Johanes","family":"Effendi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1246-5908","authenticated-orcid":false,"given":"Andros","family":"Tjandra","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5509-8963","authenticated-orcid":false,"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-3803","authenticated-orcid":false,"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Turbo learning for captionbot and drawingbot","author":"huang","year":"2018","journal-title":"arXiv 1805 08170"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref32","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/AVSP.2017-8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref36","first-page":"1857","article-title":"Learning to discover cross-domain relations with generative adversarial networks","author":"kim","year":"2017","journal-title":"Proc ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639636"},{"key":"ref34","first-page":"820","article-title":"Dual learning for machine translation","author":"he","year":"2016","journal-title":"Proc NIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003899"},{"key":"ref40","article-title":"S4L: Self-supervised semi-supervised learning","author":"zhai","year":"2019","journal-title":"arXiv 1905 03670"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref13","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref15","article-title":"Deep speaker: An end-to-end neural speaker embedding system","author":"li","year":"2017","journal-title":"arXiv 1705 02304"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"formatted","year":"2015","journal-title":"Proc ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3233\/SW-180341"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683480"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639528"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1558"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846320"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2977776"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11098-010-9508-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/11.12.1110"},{"key":"ref2","first-page":"301","article-title":"Listening while speaking: Speech chain by deep learning","author":"tjandra","year":"2017","journal-title":"Proc ASRU"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"journal-title":"The Speech Chain","year":"1993","author":"denes","key":"ref1"},{"key":"ref20","first-page":"139","article-title":"Collecting image annotations using Amazon’s mechanical turk","author":"rashtchian","year":"2010","journal-title":"Proc NAACL"},{"key":"ref22","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc NIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref24","first-page":"1","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","author":"lee","year":"2013","journal-title":"Proc ICML Workshop Challenges Represent Learn (WREPL)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_3"},{"article-title":"Learning from labeled and unlabeled data with label propagation","year":"2002","author":"zhu","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09424554.pdf?arnumber=9424554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:36Z","timestamp":1639771056000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9424554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3077886","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}