{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:12:36Z","timestamp":1781107956318,"version":"3.54.1"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icassp.2013.6637769","type":"proceedings-article","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T19:19:46Z","timestamp":1383074386000},"page":"853-857","source":"Crossref","is-referenced-by-count":42,"title":["Denoising deep neural networks based voice activity detection"],"prefix":"10.1109","author":[{"given":"Xiao-Lei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"19","first-page":"17","article-title":"On contrastive divergence learning","author":"carreira-perpinan","year":"2005","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"17","first-page":"3371","article-title":"Deep belief networks based voice activity detection","volume":"21","author":"zhang","year":"2013","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"15","first-page":"1","article-title":"Linearithmic time sparse and convex maximum margin clustering","volume":"1","author":"zhang","year":"2012","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2204978"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2011.2119482"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2011.2159374"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.02.003"},{"key":"12","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1109\/LSP.2010.2066561","article-title":"Discriminative training for multiple observation likelihood ratio based voice activity detection","volume":"17","author":"yu","year":"2010","journal-title":"IEEE Signal Process Lett"},{"key":"21","first-page":"3371","article-title":"Stacked denoising auto encoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811544"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2005.855551"},{"key":"26","first-page":"1175","article-title":"Simple and efficient multiple kernel learning by group lasso","author":"xu","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2007.913595"},{"key":"1","first-page":"2986","article-title":"Deep-structured hidden conditional random fields for phonetic recognition","author":"yu","year":"2010","journal-title":"Proc In-terspeech"},{"key":"7","first-page":"1","article-title":"Exploring monaural features for classification-based speech segregation","volume":"1","author":"wang","year":"2012","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"6","doi-asserted-by":"crossref","DOI":"10.1109\/9780470043387","author":"wang","year":"2006","journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2005.852235"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1121\/1.4754541"},{"key":"9","first-page":"1","article-title":"Towards scaling up classification-based speech separation","volume":"pp","author":"wang","year":"2013","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"8","first-page":"1","article-title":"Cocktail party processing via structured prediction","author":"wang","year":"2012","journal-title":"Proc Adv Neural Inform Process Syst"}],"event":{"name":"ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2013,5,26]]},"end":{"date-parts":[[2013,5,31]]}},"container-title":["2013 IEEE International Conference on Acoustics, Speech and Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6619549\/6637585\/06637769.pdf?arnumber=6637769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,21]],"date-time":"2017-06-21T21:01:55Z","timestamp":1498078915000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6637769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2013.6637769","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}