{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:38:03Z","timestamp":1763620683943,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003899","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"471-478","source":"Crossref","is-referenced-by-count":3,"title":["Listening While Speaking and Visualizing: Improving ASR Through Multimodal Chain"],"prefix":"10.1109","author":[{"given":"Johanes","family":"Effendi","sequence":"first","affiliation":[]},{"given":"Andros","family":"Tjandra","sequence":"additional","affiliation":[]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[]},{"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref10","first-page":"887","article-title":"Machine speech chain with one-shot speaker adaptation","year":"2018","journal-title":"Interspeech 2018 19th Annual Conference of the International Speech Communication Association"},{"key":"ref11","article-title":"End-to-end feedback loss in speech chain framework via straight-through estimator","volume":"abs 1810 13107","year":"2018","journal-title":"CoRR"},{"key":"ref12","first-page":"2764","article-title":"Wsabie: Scaling up to large vocabulary image annotation","author":"weston","year":"2011","journal-title":"Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence-Volume Volume Three"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"journal-title":"Tacotron Towards end-to-end speech synthesis","year":"2017","author":"wang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref16","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref19","volume":"abs 1604 6838","author":"dong","year":"2016","journal-title":"Word2visualvec Cross-media retrieval by visual feature prediction"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/AVSP.2017-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1163"},{"key":"ref27","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE 2011 workshop on automatic speech recognition and understanding no CONF IEEE Signal Processing Society"},{"key":"ref3","first-page":"820","article-title":"Dual learning for machine translation","author":"he","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref5","first-page":"1857","article-title":"Learning to discover cross-domain relations with generative adversarial networks","volume":"70","author":"kim","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"132","DOI":"10.21437\/Interspeech.2017-405","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref9","volume":"abs 1707 4879","author":"tjandra","year":"2017","journal-title":"Listening while speaking Speech chain by deep learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3233\/SW-180341"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-049-6_020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639528"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2019,12,14]]},"location":"SG, Singapore","end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003899.pdf?arnumber=9003899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:49:24Z","timestamp":1658155764000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003899\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003899","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}