{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:36:28Z","timestamp":1784392588641,"version":"3.55.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9415081","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6803-6807","source":"Crossref","is-referenced-by-count":29,"title":["A Hybrid CNN-BiLSTM Voice Activity Detector"],"prefix":"10.1109","author":[{"given":"Nicholas","family":"Wilkinson","sequence":"first","affiliation":[{"name":"Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Niesler","sequence":"additional","affiliation":[{"name":"Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-463","article-title":"Speech\/non-speech discrimination combining advanced feature extraction and svm learning","author":"ramirez","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2008.0128"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2011.2159374"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2013-203","article-title":"Speech activity detection on youtube using deep neural networks","author":"ryant","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2505415"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1328"},{"key":"ref18","article-title":"Semi-supervised acoustic modelling for five-lingual code-switched ASR using automatically-segmented soap opera speech","author":"wilkinson","year":"2020","journal-title":"Proc 1st Joint SLTU and CCURL Workshop"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","article-title":"Digital Cellular Telecommunications System (Phase 2+); Full Rate Speech; Voice Activity Detector (VAD) for full rate speech traffic channels","year":"1999","journal-title":"Standard GSM 06 32 version 8 0 1"},{"key":"ref6","article-title":"Voice activity detection based on generalized gamma distribution","author":"shin","year":"2005","journal-title":"Proc ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.815518"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2005.855551"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.874403"},{"key":"ref2","article-title":"A silence compression scheme for ITU-T G.729 optimized for terminals conforming to ITU-T V.70","year":"1996","journal-title":"Standard ITU-T G 729 Annex B"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2002.1179987"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1959.tb03892.x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2800728"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2028"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc International Conference on Learning Representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-268"},{"key":"ref26","article-title":"The WebRTC project","year":"2011"},{"key":"ref25","article-title":"Comparison of time-frequency representations for environmental sound classification using convolutional neural networks","author":"huzaifah","year":"2017"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09415081.pdf?arnumber=9415081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T21:02:56Z","timestamp":1725051776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9415081","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}