{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:38:39Z","timestamp":1730198319116,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/apsipaasc47483.2019.9023262","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T17:03:54Z","timestamp":1583514234000},"page":"1173-1178","source":"Crossref","is-referenced-by-count":4,"title":["Voice Activity Detection Based on Time-Delay Neural Networks"],"prefix":"10.1109","author":[{"given":"Ye","family":"Bai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"IEEE 2011 workshop on automatic speech recognition and understanding no EPFL-CONF-192584 IEEE Signal Processing Society"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref31","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"Computer Science"},{"key":"ref30","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"0","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(87)90015-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2002.1179987"},{"key":"ref12","first-page":"i","article-title":"Optimizing speech\/non-speech classifier design using adaboost","volume":"1","author":"kwon","year":"0","journal-title":"Acoustics Speech and Signal Processing 2003 Proceedings (ICASSP &#x2018;03) 2003 IEEE International Conference on"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref14","article-title":"Wavenet: A generative model for raw audio","author":"van","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref17","first-page":"728","article-title":"Speech activity detection on youtube using deep neural networks","author":"ryant","year":"2013","journal-title":"InterSpeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936602"},{"key":"ref19","article-title":"Boosted deep neural networks and multiresolution cochleagram features for voice activity detection","author":"zhang","year":"0","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref28","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"0","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1049\/ip-i-2.1992.0052"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1981.1163642"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1977.1170330"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2131131"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674443"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1975.tb02840.x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2003.813679"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.848229"},{"key":"ref20","article-title":"A universal vad based on jointly trained deep neural networks","author":"wang","year":"0","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-496"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854054"},{"key":"ref23","first-page":"3497","article-title":"The ibm speech activity detection system for the darpa rats program","author":"saon","year":"2013","journal-title":"InterSpeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472768"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2800728"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2019,11,18]]},"location":"Lanzhou, China","end":{"date-parts":[[2019,11,21]]}},"container-title":["2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8989870\/9023008\/09023262.pdf?arnumber=9023262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:49:31Z","timestamp":1658094571000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023262\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023262","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}