{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:48:01Z","timestamp":1782834481836,"version":"3.54.5"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003827","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"276-283","source":"Crossref","is-referenced-by-count":40,"title":["Advances in Online Audio-Visual Meeting Transcription"],"prefix":"10.1109","author":[{"given":"Takuya","family":"Yoshioka","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Igor","family":"Abramovski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cem","family":"Aksoylar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moshe","family":"David","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Dimitriadis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilya","family":"Gurvich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuedong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aviv","family":"Hurvitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sharon","family":"Koubi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eyal","family":"Krupka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ido","family":"Leichter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Partha","family":"Parthasarathy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alon","family":"Vinnikov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingfeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wayne","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenghao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639593"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2163395"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2050519"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2210879"},{"key":"ref36","article-title":"Variational Bayesian inference for audio-visual tracking of multiple speakers","volume":"abs 1809 10961","author":"ban","year":"2018","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1109\/TASL.2011.2164527","article-title":"Low-latency realtime meeting recognition and understanding using distant microphones and omni -directional camera","volume":"20","author":"hori","year":"0","journal-title":"IEEE Trans Audio Speech Language Process"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref2","first-page":"373","article-title":"The Rich Transcription 2007 meeting recognition evaluation","author":"fiscus","year":"0","journal-title":"Multimodal Technologies for Perception of Humans International Evaluation Workshops CLEAR 2007 and RT 2007"},{"key":"ref1","article-title":"Speech recognition for medical conversations","volume":"abs 1711 7274","author":"chiu","year":"2017","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref21","article-title":"Building corpora for single-channel speech separation across multiple domains","volume":"abs 1811 2641","author":"maciejewski","year":"2018","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2284"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1167"},{"key":"ref26","first-page":"293","article-title":"Analysis of overlaps in meetings by dialog factors, hot spots, speakers, and collection site: Insights for automatic speech recognition","author":"cetin","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682274"},{"key":"ref50","first-page":"1345","article-title":"Clustering on the unit hypersphere using von Mises-Fisher distributions","volume":"6","author":"banerjee","year":"2005","journal-title":"J Machine Learning Research"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587533"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461669"},{"key":"ref56","article-title":"Meeting transcription using virtual microphone arrays","volume":"abs 1905 2545","author":"yoshioka","year":"0","journal-title":"CoRR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953176"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995566"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00356"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-166"},{"key":"ref11","article-title":"Fully supervised speaker diarization","volume":"abs 1810 4719","author":"zhang","year":"2018","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.832994"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.838775"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2053027"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2051355"},{"key":"ref17","first-page":"268","article-title":"Relaxed disjointness based clustering for joint blind source separation and dereverberation","author":"ito","year":"2014","journal-title":"Proceedings of the Intl Workshop on Acoustic Echo and Noise Control"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-187"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref6","article-title":"English conversational telephone speech recognition by humans and machines","volume":"abs 1703 2136","author":"saon","year":"2017","journal-title":"CoRR"},{"key":"ref5","article-title":"Achieving human parity in conversational speech recognition","volume":"abs 1610 5256","author":"xiong","year":"2016","journal-title":"CoRR"},{"key":"ref8","first-page":"36","article-title":"The USTC-iFlytek system for CHiME-4 challenge","author":"du","year":"2016","journal-title":"Proc CHiME Workshop"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"399","DOI":"10.21437\/Interspeech.2017-234","article-title":"Acoustic modeling for Google Home","author":"li","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760429"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3088"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462081"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"SG, Singapore","start":{"date-parts":[[2019,12,14]]},"end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003827.pdf?arnumber=9003827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:44:16Z","timestamp":1658155456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003827","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}