{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:23Z","timestamp":1775229983756,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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","award":["61901265"],"award-info":[{"award-number":["61901265"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Pujiang Program","award":["19PJ1406300"],"award-info":[{"award-number":["19PJ1406300"]}]},{"name":"State Key Laboratory of Media Convergence Production Technology and Systems","award":["SKLMCPTS2020003"],"award-info":[{"award-number":["SKLMCPTS2020003"]}]},{"name":"Startup Fund for Youngman Research at SJTU","award":["19X100040009"],"award-info":[{"award-number":["19X100040009"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3073596","type":"journal-article","created":{"date-parts":[[2021,4,15]],"date-time":"2021-04-15T22:27:45Z","timestamp":1618525665000},"page":"1542-1555","source":"Crossref","is-referenced-by-count":35,"title":["Voice Activity Detection in the Wild: A Data-Driven Approach Using Teacher-Student Training"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4330-8980","authenticated-orcid":false,"given":"Heinrich","family":"Dinkel","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1523-9631","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xuenan","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5599-8707","authenticated-orcid":false,"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7102-9826","authenticated-orcid":false,"given":"Kai","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-458"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2057192"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0995"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1431"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1151"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref34","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.07.005"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472768"},{"key":"ref29","first-page":"29","article-title":"The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions","author":"hirsch","year":"0","journal-title":"Proc ICSLP"},{"key":"ref2","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1049\/el:20000192"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2811740"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0997"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2285"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1776"},{"key":"ref23","first-page":"704","article-title":"A robust frontend for VAD: Exploiting contextual, discriminative and spectral cues of human voice","author":"segbroeck","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1354"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref53","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"snyder","year":"2015"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2895254"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2237903"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125953"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-406"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637769"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2069750"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2011.04.005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref18","first-page":"728","article-title":"Speech activity detection on youtube using deep neural networks","author":"ryant","year":"2013","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854054"},{"key":"ref4","first-page":"1371","article-title":"A study of endpoint detection algorithms in adverse conditions: Incidence on a DTW and HMM recognizer","author":"junqua","year":"0","journal-title":"Proc 2nd European Conf on Speech Communication and Technology"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1975.tb02840.x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947431"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1977.1162964"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.005"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1928"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461392"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3054313"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref41","first-page":"19","article-title":"Large-scale weakly labeled semi-supervised sound event detection in domestic environments","author":"serizel","year":"0","journal-title":"Proc Detection Classification Acoust Scenes Events 2018 Workshop"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053459"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09405474.pdf?arnumber=9405474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:59Z","timestamp":1652194439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9405474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3073596","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}