{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:12:55Z","timestamp":1775913175299,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2018,3,1]],"date-time":"2018-03-01T00:00:00Z","timestamp":1519862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"French National Agency for Research"},{"name":"Speech and Language Technologies for Security Applications","award":["ANR-14-CE28-0021"],"award-info":[{"award-number":["ANR-14-CE28-0021"]}]},{"name":"Intelligence Advanced Research Projects Activity via Department of Defense U.S. Army Research Laboratory","award":["W911NF-12-C-0013"],"award-info":[{"award-number":["W911NF-12-C-0013"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1109\/taslp.2017.2769220","type":"journal-article","created":{"date-parts":[[2017,11,8]],"date-time":"2017-11-08T19:22:24Z","timestamp":1510168944000},"page":"646-656","source":"Crossref","is-referenced-by-count":74,"title":["Optimization of RNN-Based Speech Activity Detection"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3402-2446","authenticated-orcid":false,"given":"Gregory","family":"Gelly","sequence":"first","affiliation":[]},{"given":"Jean-Luc","family":"Gauvain","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref38","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"Neural Netw Mach Learning"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/469723"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2012.01.005"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2004.1330875"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2514\/6.2009-5664"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298623"},{"key":"ref36","article-title":"RMSPROP loses to SMORMS3","author":"funk","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/4235.985692"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MHS.1995.494215"},{"key":"ref10","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":"ref40","article-title":"An adaptive low dimensional quasi-Newton sum of functions optimizer","author":"sohl-dickstein","year":"2013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198810"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2495219"},{"key":"ref15","first-page":"728","article-title":"Speech activity detection on youtube using deep neural networks","author":"ryant","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472768"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref19","first-page":"1033","article-title":"Learning recurrent neural networks with hessian-free optimization","author":"martens","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1981.1163642"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref3","article-title":"Noise robust voice activity detection","author":"khoa","year":"2012"},{"key":"ref6","first-page":"369","article-title":"Voicing features for robust speech detection","volume":"2","author":"kristjansson","year":"2005","journal-title":"Entropy"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"685","DOI":"10.21437\/Interspeech.2005-197","article-title":"Speech event detection using multiband modulation energy","author":"evangelopoulos","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.002"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-776","article-title":"Noise robust voice activity detection using features extracted from the time-domain autocorrelation function","author":"ghaemmaghami","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-108","article-title":"A comparative study of speech detection methods","volume":"97","author":"van gerven","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052803"},{"key":"ref1","first-page":"2650","article-title":"Minimum word error training of RNN-based voice activity detection","author":"gelly","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639349"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref22","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","volume":"3","author":"gers","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref21","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","volume":"28","author":"pascanu","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2012.6269851"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref41","article-title":"NIST open speech-activity-detection evaluation","author":"sanders","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref44","first-page":"2484","article-title":"Developing STT and KWS systems using limited language resources","author":"le","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/15.11.937"},{"key":"ref43","article-title":"Segmentation et identification audiovisuelle de personnes dans des journaux télévisés","author":"gay","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8253682\/08100927.pdf?arnumber=8100927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,6]],"date-time":"2022-08-06T20:56:29Z","timestamp":1659819389000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8100927\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2769220","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3]]}}}