{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:14:02Z","timestamp":1781972042032,"version":"3.54.5"},"reference-count":56,"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.2011.2164527","type":"journal-article","created":{"date-parts":[[2011,8,16]],"date-time":"2011-08-16T19:16:09Z","timestamp":1313522169000},"page":"499-513","source":"Crossref","is-referenced-by-count":58,"title":["Low-Latency Real-Time Meeting Recognition and Understanding Using Distant Microphones and Omni-Directional Camera"],"prefix":"10.1109","volume":"20","author":[{"given":"Takaaki","family":"Hori","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoko","family":"Araki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masakiyo","family":"Fujimoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takanobu","family":"Oba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsunori","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuhiro","family":"Otsuka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Mikami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keisuke","family":"Kinoshita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsushi","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junji","family":"Yamato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960584"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860838"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495028"},{"key":"ref31","first-page":"141","article-title":"A comparative study of discriminative methods for reranking LVCSR n-best hypotheses in domain adaptation and generalization","volume":"1","author":"zhou","year":"2006","journal-title":"Proc ICASSP'06"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.06.006"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.21437\/Interspeech.2008-260","article-title":"Discriminative rescoring based on minimization of word errors for transcribing broadcast news","author":"kobayashi","year":"2008","journal-title":"Proc Interspeech'08"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"557","DOI":"10.21437\/Interspeech.2005-340","article-title":"Generalized fast on-the-fly composition algorithm for WFST-based speech recognition","author":"hori","year":"2005","journal-title":"Proc Interspeech-Eurospeech"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.889790"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"289","DOI":"10.21437\/Interspeech.2004-140","article-title":"Fast on-the-fly composition for weighted finite-state transducers in 1.8 million-word vocabulary continuous speech recognition","volume":"1","author":"hori","year":"2004","journal-title":"Proc InterSpeech-ICSLP"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607087"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/89.466659"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596042"},{"key":"ref2","article-title":"The ICSI meeting project: Resources and research","author":"janin","year":"2004","journal-title":"Proc ICASSP Meeting Recognition Workshop"},{"key":"ref1","first-page":"281","article-title":"Meeting browser: Tracking and summarizing meetings","author":"waibel","year":"1998","journal-title":"Proc Broadcast News Transcription and Understanding Workshop"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1833","DOI":"10.1016\/j.sigpro.2007.02.003","article-title":"Underdetermined blind sparse source separation for arbitrarily arranged multiple sensors","volume":"77","author":"araki","year":"2007","journal-title":"Signal Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e91-d.3.467"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828640"},{"key":"ref23","article-title":"Two-stage mel-warped Wiener filter for robust speech recognition","author":"agarwal","year":"1999","journal-title":"Proc ASRU 99"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876778"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2010.07.006"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206661"},{"key":"ref56","first-page":"2909","article-title":"Dynamic mixture models for multiple time-series","author":"wei","year":"2007","journal-title":"Proceedings of IJCAI-07"},{"key":"ref55","year":"0","journal-title":"The 2009 (RT-09) Rich Transcription Meeting Recognition Evaluation Plan"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/980451.980915"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"ref52","first-page":"244","article-title":"A Japanese national project on spontaneous speech corpus and processing technology","author":"furui","year":"2000","journal-title":"Proc ASR"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.21437\/Interspeech.2009-356","article-title":"A study of mutual front-end processing method based on statistical model for noise robust speech recognition","author":"fujimoto","year":"2009","journal-title":"Proc Interspeech'09"},{"key":"ref11","first-page":"sp-6","article-title":"NTT speech recognizer with outlook on the next generation: SOLON","author":"hori","year":"2004","journal-title":"Proc NTT Workshop on Communication Scene Analysis"},{"key":"ref40","first-page":"1741","article-title":"Towards automatic closed captioning: Low latency real time broadcast news transcription","author":"saraclar","year":"2002","journal-title":"Proc ICSLP'02"},{"key":"ref12","first-page":"509","article-title":"The ICSI RT07s speaker diarization system","author":"wooters","year":"2008","journal-title":"Multimodal Technologies for Perception of Humans International Evaluation Workshops CLEAR 2007 and RT 2007"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.906197"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045183"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2009015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2049684"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4517554"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/27616"},{"key":"ref3","first-page":"12","article-title":"Browsing recorded meetings with Ferret","author":"wellner","year":"2004","journal-title":"ICMI-MLMI"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2008.4777842"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430116"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1647314.1647356"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1452392.1452446"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.3.4-5.993"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"2119","DOI":"10.21437\/Interspeech.2009-606","article-title":"Real-time ASR from meetings","author":"garner","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878255"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.01.001"},{"key":"ref48","first-page":"1427","article-title":"Topic tracking model for analyzing consumer purchase behavior","author":"iwata","year":"2009","journal-title":"Proc IJCAI'09"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E93.D.1272"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72847-4_71"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198845"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69568-4_29"},{"key":"ref43","article-title":"Towards audio-visual on-line diarization of participants in group meetings","author":"hung","year":"2008","journal-title":"Proc Workshop Multi-Camera and Multi-Modal Sensor Fusion Algorithms and Applications"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/6099652\/05983476.pdf?arnumber=5983476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T20:40:51Z","timestamp":1638304851000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5983476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,2]]},"references-count":56,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2011.2164527","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,2]]}}}