{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T15:12:31Z","timestamp":1725721951497},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1109\/iwssip.2016.7502768","type":"proceedings-article","created":{"date-parts":[[2016,7,4]],"date-time":"2016-07-04T17:04:09Z","timestamp":1467651849000},"page":"1-4","source":"Crossref","is-referenced-by-count":4,"title":["Multi-speaker voice activity detection using a camera-assisted microphone array"],"prefix":"10.1109","author":[{"given":"Trond F.","family":"Bergh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ines","family":"Hafizovic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sverre","family":"Holm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Detection Estimation and Modulation TheoryPart IV Optimum Array Processing","year":"2004","author":"van trees","key":"ref33"},{"key":"ref32","first-page":"593","article-title":"Good features to track","author":"shi","year":"1994","journal-title":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/3-540-45103-X_50","article-title":"Two-Frame Motion Estimation Based on Polynomial Expansion","author":"farneb\u00e4ck","year":"2003","journal-title":"Image Analysis Ser Lecture Notes in Computer Science"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1168654"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.855842"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSYM.2010.5685456"},{"key":"ref12","first-page":"732","article-title":"Speaker and noise independent voice activity detection","author":"germain","year":"2013","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2004.831181"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540183"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WPNC.2007.353619"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1452392.1452446"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960522"},{"key":"ref18","first-page":"609","article-title":"Voice activity detection using visual information","author":"liu","year":"2004","journal-title":"Proc IEEE InternationalConference Acoustics Speech and Signal Processing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660092"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009715923555"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.922063"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2014.6900767"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701823"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.905996"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2011.07.009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/89.848229"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/89.985548"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2001.1034599"},{"article-title":"A high-accuracy, low-latency technique for talker localization in reverberant environments using microphone arrays","year":"2000","author":"dibiase","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.002"},{"key":"ref20","first-page":"1","article-title":"Using audio-visual features for robust voice activity detection in clean and noisy speech","author":"almajai","year":"2008","journal-title":"16th European Signal Processing Conference"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2463722"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2011.5942412"},{"key":"ref24","first-page":"556","article-title":"Voice activity detection using MFCC features and support vector machine","author":"kinnunen","year":"2007","journal-title":"Int Conf on Speech and Computers"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2011.2159374"},{"key":"ref25","first-page":"4391","article-title":"Study on the MFCC similarity-based voice activity detection algorithm","author":"wang","year":"2011","journal-title":"2nd International Conference on Artificial Intelligence Management Science and Electronic Commerce"}],"event":{"name":"2016 International Conference on Systems, Signals and Image Processing (IWSSIP)","start":{"date-parts":[[2016,5,23]]},"location":"Bratislava, Slovakia","end":{"date-parts":[[2016,5,25]]}},"container-title":["2016 International Conference on Systems, Signals and Image Processing (IWSSIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7501054\/7502689\/07502768.pdf?arnumber=7502768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T13:47:54Z","timestamp":1498312074000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7502768\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iwssip.2016.7502768","relation":{},"subject":[],"published":{"date-parts":[[2016,5]]}}}