{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:22Z","timestamp":1775229982468,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T00:00:00Z","timestamp":1533081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["10076757"],"award-info":[{"award-number":["10076757"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/lsp.2018.2811740","type":"journal-article","created":{"date-parts":[[2018,3,8]],"date-time":"2018-03-08T19:19:51Z","timestamp":1520536791000},"page":"1181-1185","source":"Crossref","is-referenced-by-count":79,"title":["Voice Activity Detection Using an Adaptive Context Attention Model"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3344-4591","authenticated-orcid":false,"given":"Juntae","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1953-6078","authenticated-orcid":false,"given":"Minsoo","family":"Hahn","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"HAVIC pilot transcription LDC2016V01","author":"tracey","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref33","first-page":"3528","article-title":"Gradient estimation using stochastic computation graphs","author":"schulman","year":"0","journal-title":"Proc 28th Int Conf Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"152","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref31","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"1","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","article-title":"FaNT: Filtering and noise adding tool","author":"hirsch","year":"2005"},{"key":"ref36","article-title":"General series 6000 combo","year":"2012"},{"key":"ref35","article-title":"TIMIT acoustic-phonetic continuous speech corpus","author":"garofolo","year":"1993"},{"key":"ref34","first-page":"1","article-title":"Understanding how image quality affects deep neural networks","author":"samuel","year":"0","journal-title":"Proc 8th International Conference on Quality of Multimedia Experience"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref40","article-title":"VAD-Toolkit","author":"kim","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125953"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.21437\/Eurospeech.2001-446","article-title":"Entropy based voice activity detection in very noisy conditions","author":"renevey","year":"2001","journal-title":"Proc EUROSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2404035"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052803"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495611"},{"key":"ref16","first-page":"127","article-title":"DySANA: Dynamic speech and noise adaptation for voice activity detection","author":"weiss","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e91-d.3.467"},{"key":"ref18","first-page":"728","article-title":"Speech activity detection on YouTube using deep neural networks","author":"ryant","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1184"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2505415"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"3118","DOI":"10.21437\/Interspeech.2010-776","article-title":"Noise robust voice activity detection using features extracted from the time-domain autocorrelation function","author":"ghaemmaghami","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3015166.3015207"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2009.2038507"},{"key":"ref6","article-title":"Noise robust voice activity detection","author":"khoa","year":"2012"},{"key":"ref29","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"0","journal-title":"Proc 27th Int Conf Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2476762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.09.0209.0104"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/35.620527"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2237903"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1155\/ASP.2005.487"},{"key":"ref46","first-page":"402","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","author":"caruana","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727633"},{"key":"ref45","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854054"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2495219"},{"key":"ref42","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-53753-5_4"},{"key":"ref41","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-268"},{"key":"ref44","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref43","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8395241\/08309294.pdf?arnumber=8309294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T17:47:05Z","timestamp":1660585625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8309294\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":46,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lsp.2018.2811740","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8]]}}}