{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:02Z","timestamp":1775229782823,"version":"3.50.1"},"publisher-location":"ISCA","reference-count":0,"publisher":"ISCA","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.21437\/interspeech.2024-978","type":"proceedings-article","created":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T07:10:12Z","timestamp":1725174612000},"page":"1375-1379","source":"Crossref","is-referenced-by-count":2,"title":["MaViLS, a Benchmark Dataset for Video-to-Slide Alignment, Assessing Baseline Accuracy with a Multimodal Alignment Algorithm Leveraging Speech, OCR, and Visual Features"],"prefix":"10.21437","author":[{"given":"Katharina","family":"Anderer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Reich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"W\u00f6lfel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"8866","published-online":{"date-parts":[[2024,9,1]]},"event":{"name":"Interspeech 2024","acronym":"interspeech_2024"},"container-title":["Interspeech 2024"],"original-title":[],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T20:25:08Z","timestamp":1731097508000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.isca-archive.org\/interspeech_2024\/anderer24_interspeech.html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,1]]},"references-count":0,"URL":"https:\/\/doi.org\/10.21437\/interspeech.2024-978","relation":{},"subject":[],"published":{"date-parts":[[2024,9,1]]}}}