{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:50:06Z","timestamp":1768074606468,"version":"3.49.0"},"publisher-location":"ISCA","reference-count":0,"publisher":"ISCA","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.21437\/interspeech.2023-1581","type":"proceedings-article","created":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T08:22:20Z","timestamp":1692001340000},"page":"2743-2747","source":"Crossref","is-referenced-by-count":1,"title":["GRAVO: Learning to Generate Relevant Audio from Visual Features with Noisy Online Videos"],"prefix":"10.21437","author":[{"given":"Youngdo","family":"Ahn","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong Won","family":"Shin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"8866","published-online":{"date-parts":[[2023,8,20]]},"event":{"name":"INTERSPEECH 2023","acronym":"interspeech_2023"},"container-title":["INTERSPEECH 2023"],"original-title":[],"deposited":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T10:18:05Z","timestamp":1705400285000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.isca-archive.org\/interspeech_2023\/ahn23b_interspeech.html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,20]]},"references-count":0,"URL":"https:\/\/doi.org\/10.21437\/interspeech.2023-1581","relation":{},"subject":[],"published":{"date-parts":[[2023,8,20]]}}}