{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T01:13:56Z","timestamp":1725585236502},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053322","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"6424-6428","source":"Crossref","is-referenced-by-count":1,"title":["Recurrent Neural Audiovisual Word Embeddings for Synchronized Speech and Real-Time Mri"],"prefix":"10.1109","author":[{"given":"Oyku Deniz","family":"Kose","sequence":"first","affiliation":[]},{"given":"Murat","family":"Saraclar","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"The MOCHA-TIMIT articulatory database","year":"1999","author":"wrench","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.24997"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1998.698623"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.404204"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.4890284"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178893"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462401"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639582"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461612"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.03.003"},{"key":"ref19","first-page":"410","article-title":"Fixed-dimensional acoustic embeddings of variablelength segments in low-resource settings","author":"levin","year":"2013","journal-title":"Proc ASRU"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683826"},{"key":"ref4","article-title":"Articulatory movement prediction using deep bidirectional long short-term memory based recurrent neural networks and word\/phone embeddings","author":"zhu","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref27","first-page":"222","article-title":"Enhanced airway-tissue boundary segmentation for real-time magnetic resonance imaging data","author":"kim","year":"2014","journal-title":"Proc ISSPIT"},{"key":"ref3","first-page":"199","article-title":"Multiview learning of word embeddings via cca","author":"dhillon","year":"2011","journal-title":"Proc NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472619"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref5","first-page":"410","article-title":"Fixed-dimensional acoustic embeddings of variablelength segments in low-resource settings","author":"levin","year":"2013","journal-title":"Proc ASRU"},{"key":"ref8","article-title":"Multi-view recurrent neural acoustic word embeddings","author":"he","year":"2017","journal-title":"Proc ICLR"},{"key":"ref7","first-page":"503","article-title":"Discriminative acoustic word embeddings: Recurrent neural network-based approaches","author":"settle","year":"2016","journal-title":"Proc SLT"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683540"},{"key":"ref1","first-page":"2042","article-title":"Convolutional neural network architectures for matching natural language sentences","author":"hu","year":"2014","journal-title":"Proc NIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178970"},{"key":"ref22","first-page":"237","article-title":"Deep multimodal semantic embeddings for speech and images","author":"harwath","year":"2015","journal-title":"Proc ASRU"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-82"},{"key":"ref24","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Proc NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"key":"ref26","article-title":"Multilingual distributed representations without word alignment","author":"hermann","year":"2014","journal-title":"Proc ICLR"},{"key":"ref25","first-page":"435","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"Proc ECCV"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053322.pdf?arnumber=9053322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:10:27Z","timestamp":1656360627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053322","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}