{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T15:57:34Z","timestamp":1782403054169,"version":"3.54.5"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448450","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11366-11370","source":"Crossref","is-referenced-by-count":4,"title":["ViLaS: Exploring the Effects of Vision and Language Context in Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Ziyi","family":"Ni","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minglun","family":"Han","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feilong","family":"Chen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linghui","family":"Meng","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Shi","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pin","family":"Lv","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-412"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953112"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383560"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639551"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.01.035"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846320"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlpbt-1.2"},{"key":"ref16","article-title":"Fine-grained grounding for multi-modal speech recognition","volume-title":"EMNLP (Findings)","author":"Srinivasan"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383466"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.127"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1179"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746801"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-423"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747118"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2986"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415054"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747101"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1107"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-697"},{"key":"ref32","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref33","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL-HLT","author":"Devlin"},{"key":"ref34","article-title":"Avatar: Unconstrained audiovisual speech recognition","author":"Valentin","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref39","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"ICLR","author":"Ren"},{"key":"ref40","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref46","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw56347.2022.00504"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448450.pdf?arnumber=10448450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:54:03Z","timestamp":1722660843000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448450\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448450","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}