{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T15:10:36Z","timestamp":1777389036331,"version":"3.51.4"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["576\/16"],"award-info":[{"award-number":["576\/16"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["1490\/16"],"award-info":[{"award-number":["1490\/16"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1109\/taslp.2017.2690568","type":"journal-article","created":{"date-parts":[[2017,5,23]],"date-time":"2017-05-23T21:03:22Z","timestamp":1495573402000},"page":"1322-1334","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal Kernel Method for Activity Detection of Sound Sources"],"prefix":"10.1109","volume":"25","author":[{"given":"David","family":"Dov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronen","family":"Talmon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Israel","family":"Cohen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Making Laplacians commute","author":"bronstein","year":"2013"},{"key":"ref38","first-page":"623","article-title":"Two-manifold problems with applications to nonlinear system identification","author":"boots","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref33","first-page":"1413","article-title":"Co-regularized multi-view spectral clustering","author":"kumar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5157-z"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587353"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273642"},{"key":"ref37","first-page":"773","article-title":"Affinity aggregation for spectral clustering","author":"huang","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248029"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.183"},{"key":"ref34","first-page":"393","article-title":"A co-training approach for multi-view spectral clustering","author":"kumar","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICSEE.2016.7806062"},{"key":"ref62","article-title":"Getting started with the DARPA TIMIT CD-ROM: An acoustic-phonetic continous speech database","author":"garofolo","year":"1993"},{"key":"ref61","first-page":"2694","article-title":"A robust audio-visual speech recognition using audio-visual voice activity detection","author":"tamura","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806238"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1031596100"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623673"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780317"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2006.04.006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1684(01)00128-1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2566919"},{"key":"ref20","first-page":"-329i","article-title":"Audio-visual synchrony for detection of monologues in video archives","volume":"1","author":"iyengar","year":"0","journal-title":"Proc 2003 IEEE Int Conf Multimedia and Expo"},{"key":"ref22","first-page":"2486","article-title":"Audio-based nonlinear video diffusion","author":"casanovas","year":"0","journal-title":"Proc 2010 IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.888095"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2360141"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638316"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1126\/science.295.5552.7a","article-title":"The isomap algorithm and topological stability","volume":"295","author":"balasubramanian","year":"2002","journal-title":"Science"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","article-title":"Nonlinear dimensionality reduction by locally linear embedding","volume":"290","author":"roweis","year":"2000","journal-title":"Science"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref51","article-title":"Mel frequency cepstral coefficients for music modeling","author":"logan","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref59","year":"0"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2405481"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2248717"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000045324.43199.43"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/BF01420984"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref53","year":"0"},{"key":"ref52","first-page":"18","article-title":"The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions","author":"hirsch","year":"0","journal-title":"Proc ASR2000-Autom Speech Recognit Challenges for the New Millenium ISCA Tutorial and Research Workshop"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-013-0567-0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"ref40","article-title":"Multiview diffusion maps","author":"lindenbaum","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2587218"},{"key":"ref13","article-title":"Acoustic scene classification using parallel combination of LSTM and CNN","author":"bae","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref16","article-title":"Sound event detection in multichannel audio using spatial and harmonic features","author":"adavanne","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2592698"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref19","first-page":"772","article-title":"Learning joint statistical models for audio-visual fusion and segregation","author":"fisher","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.872624"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205243"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886263"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2199972"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2093519"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.1262185"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2226160"},{"key":"ref46","first-page":"1","article-title":"A visual voice activity detection method with adaboosting","author":"liu","year":"0","journal-title":"Proc IET Sensor Signal Process Defence"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2009262"},{"key":"ref48","article-title":"Nonparametric canonical correlation analysis","author":"michaeli","year":"0","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2605068"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2015.09.002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2008.4813402"},{"key":"ref43","article-title":"Latent common manifold learning with alternating diffusion: Analysis and applications","author":"talmon","year":"2016"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7933016\/07933049.pdf?arnumber=7933049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:15:00Z","timestamp":1642004100000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7933049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":64,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2690568","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6]]}}}