{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T21:08:14Z","timestamp":1766869694421,"version":"3.37.3"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Korea Environment Industry & Technology Institute"},{"name":"Korea Ministry of Environment","award":["2017000210001"],"award-info":[{"award-number":["2017000210001"]}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/lsp.2019.2959917","type":"journal-article","created":{"date-parts":[[2019,12,17]],"date-time":"2019-12-17T00:25:43Z","timestamp":1576542343000},"page":"131-135","source":"Crossref","is-referenced-by-count":26,"title":["Spectro-Temporal Attention-Based Voice Activity Detection"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0725-3444","authenticated-orcid":false,"given":"Younglo","family":"Lee","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5995-7200","authenticated-orcid":false,"given":"Jeongki","family":"Min","sequence":"additional","affiliation":[]},{"given":"David K.","family":"Han","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8744-4514","authenticated-orcid":false,"given":"Hanseok","family":"Ko","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"VAD-toolkit","year":"2017","author":"kim","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2800728"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2901195"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2811740"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639066"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.07.005"},{"key":"ref15","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref16","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref18","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref19","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref27","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref29","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461921"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2769220"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-53753-5_4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2505415"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref21","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","first-page":"198","article-title":"TED-LIUM 3: Twice as much data and corpus repartition for experiments on speaker adaptation","author":"hernandez","year":"0","journal-title":"Proc Int Conf Speech Comput"},{"key":"ref25","first-page":"181","article-title":"The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions","author":"hirsch","year":"0","journal-title":"Proc Automat Speech Recognit Challenges New Millenium ISCA Tuts Res Workshop"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8966529\/08933025.pdf?arnumber=8933025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:46:28Z","timestamp":1651070788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8933025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/lsp.2019.2959917","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2020]]}}}