{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:47:16Z","timestamp":1765547236619,"version":"3.28.0"},"reference-count":26,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446901","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6385-6389","source":"Crossref","is-referenced-by-count":3,"title":["OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset"],"prefix":"10.1109","author":[{"given":"Jeongkyun","family":"Park","sequence":"first","affiliation":[{"name":"Sogang University,Department of Artificial Intelligence,Seoul,Republic of Korea,04107"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jung-Wook","family":"Hwang","sequence":"additional","affiliation":[{"name":"Sogang University,Department of Electronic Engineering,Seoul,Republic of Korea,04107"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwanghee","family":"Choi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,PA,USA,15213"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seung-Hyeon","family":"Lee","sequence":"additional","affiliation":[{"name":"Sogang University,Department of Electronic Engineering,Seoul,Republic of Korea,04107"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun Hwan","family":"Ahn","sequence":"additional","affiliation":[{"name":"Mindslab Inc.,Gyeonggi-do,Republic of Korea,13493"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rae-Hong","family":"Park","sequence":"additional","affiliation":[{"name":"Sogang University,Department of Electronic Engineering,Seoul,Republic of Korea,04107"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyung-Min","family":"Park","sequence":"additional","affiliation":[{"name":"Sogang University,Department of Artificial Intelligence,Seoul,Republic of Korea,04107"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163155"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-424"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","year":"2018","author":"Afouras","key":"ref4"},{"article-title":"Lip reading in profile","volume-title":"Proc. British Machine Vision Conf","author":"Chung","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref7","first-page":"6829","article-title":"A multimodal German dataset for automatic lip reading systems and transfer learning","volume-title":"Proc. Language Resources and Evaluation Conf","author":"Schwiebert"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10483"},{"issue":"1","key":"ref9","first-page":"5","article-title":"Collection of Korean audio-video speech data","volume":"7","author":"Jo","year":"2000","journal-title":"Speech Sciences"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.922789"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/34.982900"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1006168"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2030637"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5391\/IJFIS.2019.19.1.1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/app10196936"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_22"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10446901.pdf?arnumber=10446901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:27:17Z","timestamp":1722576437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446901","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}