{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T13:05:25Z","timestamp":1762088725598,"version":"build-2065373602"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095539","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Visual Information Matters for ASR Error Correction"],"prefix":"10.1109","author":[{"given":"Vanya Bannihatti","family":"Kumar","sequence":"first","affiliation":[{"name":"ByteDance"}]},{"given":"Shanbo","family":"Cheng","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Ningxin","family":"Peng","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Yuchen","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance"}]}],"member":"263","reference":[{"article-title":"Flamingo: a visual language model for few-shot learning","year":"2022","author":"alayrac","key":"ref13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.203"},{"key":"ref15","article-title":"Ted-lium 3: twice as much data and corpus repartition for experiments on speaker adaptation","author":"hernandez","year":"2018","journal-title":"SPECOM"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2021","author":"dosovitskiy","key":"ref14"},{"article-title":"How2: A large-scale dataset for multimodal language understanding","year":"2018","author":"sanabria","key":"ref11"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref1","first-page":"27826","article-title":"Unsupervised speech recognition","volume":"34","author":"baevski","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2482"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-demo.7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"article-title":"Attention is all you need","year":"2017","author":"vaswani","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.438"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1242"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00504"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746763"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095539.pdf?arnumber=10095539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:01:00Z","timestamp":1699902060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095539\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095539","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}