{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T04:10:19Z","timestamp":1746850219482,"version":"3.40.5"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2017,11,1]],"date-time":"2017-11-01T00:00:00Z","timestamp":1509494400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2017,11,1]],"date-time":"2017-11-01T00:00:00Z","timestamp":1509494400000},"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":[[2017,11]]},"DOI":"10.1109\/icsda.2017.8384446","type":"proceedings-article","created":{"date-parts":[[2018,6,14]],"date-time":"2018-06-14T23:31:04Z","timestamp":1529019064000},"page":"1-5","source":"Crossref","is-referenced-by-count":10,"title":["Linear-scale filterbank for deep neural network-based voice activity detection"],"prefix":"10.1109","author":[{"given":"Youngmoon","family":"Jung","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Younggwan","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyungjun","family":"Lim","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hoirin","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-268"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-136"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472768"},{"key":"ref13","first-page":"704","article-title":"A robust frontend for VAD: Exploiting contextual, discriminative and spectral cues of human voice","author":"van segbroeck","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163888"},{"key":"ref15","article-title":"Aurora working group: DSR front end LVCSR evaluation AU\/384\/02","author":"pearce","year":"2002","journal-title":"Inst for Signal & Inf Process Mississippi State Univ Tech Rep"},{"journal-title":"100 nonspeech environmental sounds","year":"2004","author":"hu","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2505415"},{"key":"ref18","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Stat"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.143.1.7063747"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"2086","DOI":"10.21437\/Interspeech.2010-588","article-title":"Voice activity detection based on conditional random fields using multiple features","author":"saito","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2011.02.015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref5","first-page":"728","article-title":"Speech activity detection on YouTube using deep neural networks","author":"ryant","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref8","first-page":"3497","article-title":"The IBM speech activity detection system for the DARPA RATS program","author":"saon","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854054"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2011.2159374"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"}],"event":{"name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment (O-COCOSDA)","start":{"date-parts":[[2017,11,1]]},"location":"Seoul, Korea (South)","end":{"date-parts":[[2017,11,3]]}},"container-title":["2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8373628\/8384412\/08384446.pdf?arnumber=8384446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T17:57:41Z","timestamp":1746813461000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8384446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icsda.2017.8384446","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}