{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T15:42:21Z","timestamp":1760888541570},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2012,2,1]],"date-time":"2012-02-01T00:00:00Z","timestamp":1328054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2012,2]]},"DOI":"10.1109\/tasl.2011.2151858","type":"journal-article","created":{"date-parts":[[2011,5,10]],"date-time":"2011-05-10T17:45:21Z","timestamp":1305049521000},"page":"447-460","source":"Crossref","is-referenced-by-count":17,"title":["Probabilistic Speaker Diarization With Bag-of-Words Representations of Speaker Angle Information"],"prefix":"10.1109","volume":"20","author":[{"given":"Katsuhiko","family":"Ishiguro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takeshi","family":"Yamada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoko","family":"Araki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Sawada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1322192.1322254"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1111\/j.1541-0420.2005.00381.x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828640"},{"key":"ref31","first-page":"209","volume":"12","author":"attias","year":"2000","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390260"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366611"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1865106.1865111"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518619"},{"key":"ref34","article-title":"AMI Project","year":"0","journal-title":"AMI Meeting Corpus"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390196"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459558"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366894"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2008.4538680"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/11965152_23","article-title":"Speaker diarization for multi-microphone meetings using only between-channel differences","author":"pardo","year":"2006","journal-title":"Proc Joint Workshop Multimodal Interaction and Related Mach Learn Algorithms (MLMI)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.125"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.3.4-5.993"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2009.5346517"},{"key":"ref18","first-page":"4441","article-title":"A voice activity detection based on adaptive integration of multiple speech features and a signal decision scheme","author":"fujimoto","year":"2008","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661205"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959513"},{"key":"ref4","first-page":"597","article-title":"Advances in automatic meeting record creation and access","author":"waibel","year":"2001","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref3","first-page":"373","article-title":"The rich transcription 2007 meeting recognition evaluation","volume":"4625","author":"fiscus","year":"2008","journal-title":"Proc Multimodal Technol Percept Humans Int Eval Workshops CLEAR 2007 and RT 2007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1322192.1322210"},{"key":"ref29","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641112"},{"key":"ref8","first-page":"509","article-title":"The ICSI RT07s speaker diarization systems","volume":"4625","author":"wooters","year":"2008","journal-title":"Proc Multimodal Technol Percept Humans Int Eval Workshops CLEAR 2007 and RT 2007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9054-4"},{"key":"ref9","first-page":"497","article-title":"The IBM RT07 evaluation systems for speaker diarization on lecture meetings","volume":"4625","author":"huang","year":"2008","journal-title":"Proc Multimodal Technol Percept Humans Int Eval Workshops CLEAR 2007 and RT 2007"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/11677482_3","article-title":"The AMI meeting corpus: A pre-announcement","volume":"3869","author":"carletta","year":"2006","journal-title":"Proc Multimodal Interaction and Related Machine Learning Algorithms Workshop (MLMI-05)"},{"key":"ref20","author":"duda","year":"2001","journal-title":"Pattern Classification"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587620"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587622"},{"key":"ref24","first-page":"1103","article-title":"Efficient indexing for large scale visual search","author":"zhang","year":"2009","journal-title":"Proc IEEE Int Conf Comput Vis (ICCV)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459342"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2009.5346483"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459301"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/6099652\/05765484.pdf?arnumber=5765484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:54:17Z","timestamp":1642006457000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5765484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,2]]},"references-count":38,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2011.2151858","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,2]]}}}