{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:12:41Z","timestamp":1784203961887,"version":"3.55.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icassp.2013.6637694","type":"proceedings-article","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T23:19:46Z","timestamp":1383088786000},"page":"483-487","source":"Crossref","is-referenced-by-count":145,"title":["Real-life voice activity detection with LSTM Recurrent Neural Networks and an application to Hollywood movies"],"prefix":"10.1109","author":[{"given":"Florian","family":"Eyben","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Weninger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Squartini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bjorn","family":"Schuller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"19","article-title":"The media eval 2012 affect task: Violent scenes detection in hollywood movies","author":"demarty","year":"2012","journal-title":"Proc of MediaEval 2012 Workshop"},{"key":"17","author":"garofolo","year":"1993","journal-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947689"},{"key":"15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-74690-4_56","article-title":"Multidimensional recurrent neural networks","author":"graves","year":"2007","journal-title":"Proc of the 2007 International Conference on Artificial Neural Networks"},{"key":"16","author":"pitt","year":"2007","journal-title":"Buckeye corpus of conversational speech (2nd release)"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"11","doi-asserted-by":"crossref","first-page":"2617","DOI":"10.21437\/Interspeech.2005-243","article-title":"Non-linear esimation of voice activity to improve automatic recognition of noisy speech","author":"gemello","year":"2005","journal-title":"Proc of Interspeech 2005"},{"key":"12","article-title":"Gradient flow in recurrent nets: The difficulty of learning long-term dependencies","author":"hochreiter","year":"2001","journal-title":"A Field Guide to Dynamical Recurrent Neural Networks"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947534"},{"key":"20","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-503","article-title":"Speaker-dependent voice activity detection robust to background speech noise","author":"matsuda","year":"2012","journal-title":"Proc of INTERSPEECH 2012"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2204978"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.08.005"},{"key":"24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-528","article-title":"Speech activity detection for noisy data using adaptation techniques","author":"omar","year":"2012","journal-title":"Proc of INTERSPEECH 2012"},{"key":"25","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-422","article-title":"Voice activity detection using speech recognizer feedback","author":"thambiratnam","year":"2012","journal-title":"Proc of INTERSPEECH 2012"},{"key":"26","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-531","article-title":"Acoustic and data-driven features for robust speech activity detection","author":"thomas","year":"2012","journal-title":"Proc of INTERSPEECH 2012"},{"key":"3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-529","article-title":"Speech\/nonspeech segmentation in web videos","author":"misra","year":"2012","journal-title":"Proc of INTERSPEECH 2012"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2070494"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1049\/el:20000192"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325980"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2005.855551"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"4","doi-asserted-by":"crossref","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 of INTERSPEECH 2012"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811544"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.002"}],"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\/06637694.pdf?arnumber=6637694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T22:30:03Z","timestamp":1646951403000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6637694\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2013.6637694","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}