{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T21:25:13Z","timestamp":1781731513154,"version":"3.54.5"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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"}],"funder":[{"DOI":"10.13039\/501100015749","name":"Communication University of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015749","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414445","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6823-6827","source":"Crossref","is-referenced-by-count":34,"title":["Speech Enhancement Aided End-To-End Multi-Task Learning for Voice Activity Detection"],"prefix":"10.1109","author":[{"given":"Xu","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2901195"},{"key":"ref11","article-title":"Waveform-based voice activity detection exploiting fully convolutional networks with multi-branched encoders","author":"yu","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637769"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"2282","DOI":"10.21437\/Interspeech.2015-442","article-title":"A universal VAD based on jointly trained deep neural networks","volume":"2015 janua","author":"wang","year":"2015","journal-title":"INTERSPEECH16 2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1776"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023101"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/app10093230"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1151"},{"key":"ref18","article-title":"Multi-task joint-learning for robust voice activity detection","author":"zhuang","year":"2017","journal-title":"ISCSLP 2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref28","article-title":"Voice activity detection toolkit website","author":"kim","year":"2018"},{"key":"ref4","first-page":"252","article-title":"Boosting contextual information for deep neural network based voice activity detection","volume":"24","author":"zhang","year":"2015","journal-title":"IEEE\/ACM TASLP"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854054"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2811740"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3185066.3185086"},{"key":"ref8","first-page":"1159","article-title":"Temporarily-Aware Context Modeling Using Generative Adversarial Networks for Speech Activity Detection","volume":"28","author":"fernando","year":"2020","journal-title":"IEEE\/ACM TASLP"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461921"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-268"},{"key":"ref1","first-page":"697","article-title":"Deep belief networks based voice activity detection","volume":"21","author":"zhang","year":"2012","journal-title":"IEEE\/ACM TASLP"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221459"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2005.855551"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"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\/09414445.pdf?arnumber=9414445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:29:14Z","timestamp":1672129754000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414445\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414445","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}