{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:56:52Z","timestamp":1780588612104,"version":"3.54.1"},"publisher-location":"ISCA","reference-count":0,"publisher":"ISCA","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.21437\/interspeech.2022-10920","type":"proceedings-article","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T15:42:06Z","timestamp":1663342926000},"page":"2833-2837","source":"Crossref","is-referenced-by-count":33,"title":["Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Muti-Person Video"],"prefix":"10.21437","author":[{"given":"Dmitriy","family":"Serdyuk","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Otavio","family":"Braga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Siohan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"8866","published-online":{"date-parts":[[2022,9,18]]},"event":{"name":"Interspeech 2022","acronym":"interspeech_2022"},"container-title":["Interspeech 2022"],"original-title":[],"deposited":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T10:19:32Z","timestamp":1705400372000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.isca-archive.org\/interspeech_2022\/serdyuk22_interspeech.html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,18]]},"references-count":0,"URL":"https:\/\/doi.org\/10.21437\/interspeech.2022-10920","relation":{},"subject":[],"published":{"date-parts":[[2022,9,18]]}}}