{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T13:52:27Z","timestamp":1725717147748},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022462","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"525-531","source":"Crossref","is-referenced-by-count":1,"title":["Investigating the Important Temporal Modulations for Deep-Learning-Based Speech Activity Detection"],"prefix":"10.1109","author":[{"given":"Tyler","family":"Vuong","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Department of Electrical and Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikhil","family":"Madaan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Department of Electrical and Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohan","family":"Panda","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Department of Electrical and Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard M.","family":"Stern","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Department of Electrical and Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3054"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2301"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1942"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1252"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1915"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1878"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-651"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858055"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-015-0277-z"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00032-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-104"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.409836"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-421"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414105"},{"article-title":"Leaf: A learnable frontend for audio classification","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zeghidour","key":"ref17"},{"key":"ref18","article-title":"Speech-Brain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2762739"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kingma","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-258"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2017.02.011"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022462.pdf?arnumber=10022462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:33:19Z","timestamp":1707813199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022462","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}