{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T04:00:33Z","timestamp":1725595233462},"reference-count":23,"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\/asru46091.2019.9004030","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"465-470","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Based Speech Recognition Using Gaze Information"],"prefix":"10.1109","author":[{"given":"Osamu","family":"Segawa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuya","family":"Takeda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning"},{"journal-title":"End-to-end continuous speech recognition using attention-based recurrent nn First results","year":"2014","author":"chorowski","key":"ref11"},{"journal-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","year":"2014","author":"cho","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"journal-title":"State-of-the-art speech recognition with sequence-to-sequence models","year":"2017","author":"chiu","key":"ref14"},{"key":"ref15","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref17"},{"key":"ref18","first-page":"1097","article-title":"Ima-genet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"journal-title":"ImageNet A Large-scale Hierarchical Image Database","year":"2009","author":"deng","key":"ref19"},{"journal-title":"End-to-end audiovisual speech recognition","year":"2018","author":"petridis","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0629-7"},{"journal-title":"Object referring in videos with language and human gaze","year":"2018","author":"vasudevan","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858137"},{"journal-title":"Gaze-contingent automatic speech recognition","year":"2006","author":"cooke","key":"ref8"},{"key":"ref7","first-page":"112","article-title":"Fusing eye-gaze and speech recognition for tracking in an automatic reading tutor - a step in the right direction?","author":"rasmussen","year":"2013","journal-title":"Proc SLaTE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref1","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Eleventh Annual Conference of the International Speech Communication Association"},{"journal-title":"ESPnet End-to-end speech processing toolkit","year":"2018","author":"watanabe","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref23","article-title":"Corpus of spontaneous japanese: Its design and evaluation","author":"maekawa","year":"2003","journal-title":"ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition"}],"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\/09004030.pdf?arnumber=9004030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:51:19Z","timestamp":1658155879000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9004030\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9004030","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}