{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T16:15:13Z","timestamp":1762013713182,"version":"build-2065373602"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/EU.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682750","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"8648-8652","source":"Crossref","is-referenced-by-count":14,"title":["Multimodal Grounding for Sequence-to-sequence Speech Recognition"],"prefix":"10.1109","author":[{"given":"Ozan","family":"Caglayan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramon","family":"Sanabria","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shruti","family":"Palaskar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Loic","family":"Barraul","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Places: A 10 million image database for scene recognition","author":"zhou","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref11","first-page":"6546","article-title":"Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet?","author":"hara","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref12","article-title":"How2: a large-scale dataset for multimodal language understanding","author":"sanabria","year":"2018","journal-title":"Proceedings of the Workshop on Visually Grounded Interaction and Language (ViGIL) NeurIPS"},{"key":"ref13","article-title":"Neural machine translation by jointly learning to align and translate","volume":"abs 1409 473","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref16","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume":"abs 1412 3555","author":"chung","year":"2014","journal-title":"CoRR"},{"key":"ref17","article-title":"Using the output embed-ding to improve language models","author":"press","year":"2016","journal-title":"arXiv preprint arXiv 1608 05859"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref19","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953112"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639551"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-412"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462439"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4746"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1105"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref21","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv preprint arXiv 1705 06950"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2457612"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1515\/pralin-2017-0035"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846320"},{"key":"ref25","article-title":"Recurrent neural network language model adaptation for multi-genre broadcast speech recognition","author":"chen","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682750.pdf?arnumber=8682750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:10:25Z","timestamp":1657854625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682750","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}