{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:06:54Z","timestamp":1740100014492,"version":"3.37.3"},"reference-count":22,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/icassp39728.2021.9415045","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6828-6832","source":"Crossref","is-referenced-by-count":5,"title":["Robust Voice Activity Detection Using a Masked Auditory Encoder Based Convolutional Neural Network"],"prefix":"10.1109","author":[{"given":"Nan","family":"Li","sequence":"first","affiliation":[]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Masashi","family":"Unoki","sequence":"additional","affiliation":[]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Meng","family":"Ge","sequence":"additional","affiliation":[]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-268"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3015166.3015207"},{"key":"ref12","first-page":"36","article-title":"A multi-phase gamma-tone filterbank for speech separation via tasnet","author":"ditter","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1354"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.417975"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1121\/1.2924135"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-737"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2010.05.001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.1914446"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"2624","DOI":"10.1109\/TASL.2011.2125953","article-title":"Voice activity detection based on an unsupervised learning framework","volume":"19","author":"soong","year":"2011","journal-title":"IEEE Transactions on Audio Speech & Language Processing"},{"key":"ref3","first-page":"2609","article-title":"Voice activity detection in mtf-based power envelope restoration","author":"masashi","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2505415"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019414"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-017-0482-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674386"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/35.620527","article-title":"Itu-t recommendation g.729 annex b: a silence compression scheme for use with g.729 optimized for v.70 digital simultaneous voice and data applications","volume":"35","author":"shlomot","year":"1997","journal-title":"IEEE Communications Magazine"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2800728"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.3.535"},{"key":"ref22","article-title":"Voice activity detection in mtf-based power envelope restoration","author":"unoki","year":"2011","journal-title":"12th Annual Conference of the International Speech Communication Association INTERSPEECH-2011"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","article-title":"Assessment for automatic speech recognition: Ii. noisex-92: A database and an experiment to study the effect of additive noise on speech recognition systems","volume":"12","author":"andrew","year":"1993","journal-title":"Speech Communication"}],"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\/09415045.pdf?arnumber=9415045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:50Z","timestamp":1652197250000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415045\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9415045","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}