{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T16:39:27Z","timestamp":1725727167420},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"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":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317128","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:07:46Z","timestamp":1700489266000},"page":"1857-1861","source":"Crossref","is-referenced-by-count":0,"title":["Transformer-based Automatic Speech Recognition of Simultaneous Interpretation with Auxiliary Input of Source Language Text"],"prefix":"10.1109","author":[{"given":"Shuta","family":"Taniguchi","sequence":"first","affiliation":[{"name":"Doshisha University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsuneo","family":"Kato","sequence":"additional","affiliation":[{"name":"Doshisha University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akihiro","family":"Tamura","sequence":"additional","affiliation":[{"name":"Doshisha University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keiji","family":"Yasuda","sequence":"additional","affiliation":[{"name":"Mindword, Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2162"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-343"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3254"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref10","first-page":"1","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"li","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-448"},{"key":"ref17","article-title":"Ciair simultaneous interpretation corpus","author":"tohyama","year":"2004","journal-title":"Proc Oriental COCOSDA"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2456"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1136"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3024218"},{"key":"ref9","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-281"},{"key":"ref6","first-page":"689","article-title":"Multimodal Deep Learning","author":"ngiam","year":"2011","journal-title":"Proc ICML 2011"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","article-title":"Recent advances in the automatic recognition of audio-visual speech","author":"potamianos","year":"2003","journal-title":"Proc IEEE"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2023,10,31]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317128.pdf?arnumber=10317128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T19:24:37Z","timestamp":1701372277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317128\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317128","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}