{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T14:30:58Z","timestamp":1762353058871},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413961","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6808-6812","source":"Crossref","is-referenced-by-count":10,"title":["Self-Attentive VAD: Context-Aware Detection of Voice from Noise"],"prefix":"10.1109","author":[{"given":"Yong Rae","family":"Jo","sequence":"first","affiliation":[{"name":"Voithru Inc."}]},{"given":"Young","family":"Ki Moon","sequence":"additional","affiliation":[{"name":"Voithru Inc."}]},{"given":"Won Ik","family":"Cho","sequence":"additional","affiliation":[{"name":"Seoul National University"}]},{"given":"Geun","family":"Sik Jo","sequence":"additional","affiliation":[{"name":"Inha University"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2505415"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472772"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2811740"},{"key":"ref15","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015"},{"key":"ref16","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"TIMIT acousticphonetic continuous speech corpus","author":"garofolo","year":"1992","journal-title":"Linguistic Data Consortium"},{"article-title":"MUSAN: A music, speech, and noise corpus","year":"2015","author":"snyder","key":"ref19"},{"key":"ref4","first-page":"728","article-title":"Speech activity detection on Youtube using deep neural networks","author":"ryant","year":"2013","journal-title":"INTERSPEECH Lyon France"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref5","article-title":"Entropy based voice activity detection in very noisy conditions","author":"renevey","year":"2001","journal-title":"Seventh European Conference on Speech Communication and Technology"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2495219"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.874403"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639066"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.853212"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1184"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"article-title":"Youtube-8M: A large-scale video classification benchmark","year":"2016","author":"abu-el-haija","key":"ref22"},{"article-title":"The mediaeval 2014 affect task: Violent scenes detection","year":"2014","author":"sj\u00f6berg","key":"ref21"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2359159"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413961.pdf?arnumber=9413961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:19Z","timestamp":1659486019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413961\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413961","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}