{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:28:46Z","timestamp":1776882526811,"version":"3.51.2"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2016,2,1]],"date-time":"2016-02-01T00:00:00Z","timestamp":1454284800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,2]]},"DOI":"10.1109\/taslp.2015.2505415","type":"journal-article","created":{"date-parts":[[2015,12,4]],"date-time":"2015-12-04T19:06:49Z","timestamp":1449256009000},"page":"252-264","source":"Crossref","is-referenced-by-count":118,"title":["Boosting Contextual Information for Deep Neural Network Based Voice Activity Detection"],"prefix":"10.1109","volume":"24","author":[{"given":"Xiao-Lei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854890"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref33","author":"pearce","year":"2002","journal-title":"?Aurora working group DSR front end LVCSR evaluation AU\/384\/02 ?"},{"key":"ref32","first-page":"29","article-title":"The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions","volume":"4","author":"pearce","year":"2000","journal-title":"Proc ICSLP"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2359159"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116037"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/3-540-59119-2_166","article-title":"A desicion-theoretic generalization of on-line learning and an application to boosting","author":"freund","year":"1995","journal-title":"Proc Int Conf Comput Learn Theory"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/3-540-45014-9_1","author":"dietterich","year":"2000","journal-title":"Multiple Classifiers Systems"},{"key":"ref34","author":"zhang","year":"2015","journal-title":"Boosting contextual information for deep neural network based voice activity detection"},{"key":"ref28","first-page":"291","article-title":"The RATS radio traffic collection system","author":"walker","year":"2012","journal-title":"Proc ISCA Odyssey"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854930"},{"key":"ref29","author":"wang","year":"2015","journal-title":"?Deep neural network based supervised speech segregation generalizes to novel noises through large-scale training ?"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/35.620527"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.02.003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref24","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178822"},{"key":"ref25","first-page":"1534","article-title":"Boosted deep neural networks and multi-resolution cochleagram features for voice activity detection","author":"zhang","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2363410"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2057192"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.815518"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2227738"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.874403"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2005.855551"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2237903"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2252615"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2248717"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.07.006"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1969","DOI":"10.21437\/Interspeech.2012-527","article-title":"Developing a speech activity detection system for the DARPA RATS program","author":"ng","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2002.1179987"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref3","article-title":"Speech processing, transmission and quality aspects (STQ); distributed speech recognition; advanced front-end feature extraction algorithm; compression algorithms","volume":"202","year":"0","journal-title":"ETSI ES"},{"key":"ref6","first-page":"1553","article-title":"The use of low-frequency ultrasound for voice activity detection","author":"mcloughlin","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/89.905996"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref49","article-title":"Noisex-92 database","year":"0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2404035"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125953"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2219526"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881700"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2313917"},{"key":"ref47","year":"2006","journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications"},{"key":"ref42","first-page":"1232","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref41","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":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"ref43","first-page":"1","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7370838\/7347379.pdf?arnumber=7347379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,28]],"date-time":"2022-05-28T10:12:41Z","timestamp":1653732761000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7347379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,2]]},"references-count":51,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2015.2505415","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,2]]}}}