{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:13:47Z","timestamp":1740172427951,"version":"3.37.3"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","award":["FA8750-15-1-0205"],"award-info":[{"award-number":["FA8750-15-1-0205"]}],"id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University of Texas at Dallas from the Distinguished University Chair in Telecommunications Engineering"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/taslp.2018.2848698","type":"journal-article","created":{"date-parts":[[2018,7,2]],"date-time":"2018-07-02T18:46:40Z","timestamp":1530557200000},"page":"2056-2071","source":"Crossref","is-referenced-by-count":10,"title":["Leveraging Frequency-Dependent Kernel and DIP-Based Clustering for Robust Speech Activity Detection in Naturalistic Audio Streams"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0476-3884","authenticated-orcid":false,"given":"Harishchandra","family":"Dubey","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhijeet","family":"Sangwan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1382-9929","authenticated-orcid":false,"given":"John H. L.","family":"Hansen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/2347485"},{"key":"ref38","first-page":"2726","article-title":"Robust feature clustering for unsupervised speech activity detection","author":"dubey","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref33","article-title":"Windows, harmonic analysis, and the discrete Fourier transform","author":"harris","year":"1969","journal-title":"NUC TP532 Naval Undersea Center"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1073\/pnas.42.1.43","article-title":"A central limit theorem and a strong mixing condition","volume":"42","author":"rosenblatt","year":"0","journal-title":"Proc Nat Acad Sci"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2057192"},{"key":"ref30","first-page":"123","article-title":"Supervised\/unsupervised voice activity detectors for\n text-dependent speaker recognition on the RSR2015 corpus","author":"alam","year":"0","journal-title":"Proc of the IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176346577"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4076(81)90071-3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1006\/jmps.1999.1277"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.11.004"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1174"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2237903"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2080821"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639066"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2005.855551"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846238"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-550"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052803"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2069750"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.07.006"},{"key":"ref50","article-title":"CRSS-LDNN:\n Long-duration naturalistic noise corpus containing multi-layer noise recordings for robust speech processing","author":"hansen","year":"0","journal-title":"Proc 176th Meeting Acoust Soc of Amer"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref59","first-page":"179","article-title":"Further optimisations of constant Q cepstral\n processing for integrated utterance and text-dependent speaker verification","author":"delgado","year":"0","journal-title":"Proc IEEE Spoken Lang Technol Workshop"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639060"},{"key":"ref56","first-page":"3027","article-title":"UBM\n fused total variability modeling for language identification","author":"van segbroeck","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref55","first-page":"1589","article-title":"Robust speaker identification using auditory features and computational auditory scene analysis","author":"shao","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960661"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366996"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2101594"},{"key":"ref10","first-page":"709","article-title":"All for one: feature combination for highly\n channel-degraded speech activity detection","author":"graciarena","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref11","first-page":"5","article-title":"UTDallas-PLTL: Leveraging Spoken Language Technology for Assessment of\n Communication based Learning Behavior in Peer-Led Team Learning","author":"hansen","year":"0","journal-title":"Proc 6th Annu Conf Peer-Led Team Learn Int Soc"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939740"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.4969337"},{"key":"ref13","first-page":"3169","article-title":"The zero resource speech challenge 2015.","author":"versteegh","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref14","first-page":"291","article-title":"The RATS radio traffic collection system","author":"walker","year":"0","journal-title":"Proc of the IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-603"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2495219"},{"journal-title":"DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus CD-ROM","year":"1993","author":"garofolo","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2011.2119482"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1281"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.02.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472771"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.07.005"},{"key":"ref8","first-page":"3497","article-title":"The IBM speech activity detection system for the DARPA RATS\n program","author":"saon","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref7","first-page":"1969","article-title":"Developing a speech activity detection system for the DARPA\n RATS program","author":"ng","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref49","first-page":"1","article-title":"Multi-stream audio analysis for knowledge extraction and\n understanding of small-group interactions in peer-led team learning","author":"hansen","year":"0","journal-title":"Proc 6th Annu Conf Peer-Led Team Learn Int Soc"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178822"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1497"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1121\/1.5036130"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/DSP-SPE.2015.7369526"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846283"},{"year":"2017","key":"ref42","article-title":"NIST pilot speech analytic technologies evaluation, OpenSAT"},{"year":"2015","key":"ref41","article-title":"NIST OpenSAD Challenge"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.04.002"},{"key":"ref43","first-page":"2996","article-title":"The RedDots data collection for speaker\n recognition","author":"lee","year":"0","journal-title":"Proc ISCA Interspeech"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8429900\/08401923.pdf?arnumber=8401923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T13:19:40Z","timestamp":1643203180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8401923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":63,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2848698","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}