{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:33Z","timestamp":1760245053480,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053122","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6509-6513","source":"Crossref","is-referenced-by-count":14,"title":["Multimodal Speaker Diarization of Real-World Meetings Using D-Vectors With Spatial Features"],"prefix":"10.1109","author":[{"given":"Wonjune","family":"Kang","sequence":"first","affiliation":[]},{"given":"Brandon C.","family":"Roy","sequence":"additional","affiliation":[]},{"given":"Wesley","family":"Chow","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICASSP.2018.8462628"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref12","article-title":"Speaker diarization for multiple distant microphone meetings: Mixing acoustic features and inter-channel time differences","author":"pardo","year":"2006","journal-title":"Ninth International Conference on Spoken Language Processing"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/TASL.2007.902460"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1007\/s11042-014-2274-x"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1007\/s11042-018-5944-2"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.21437\/Interspeech.2019-3116"},{"year":"2000","author":"dibiase","journal-title":"A High-Accuracy Low-Latency Technique for Talker Localization in Reverberant Environments Using Microphone Arrays","key":"ref17"},{"key":"ref18","first-page":"100","article-title":"The AMI meeting corpus","volume":"88","author":"mccowan","year":"2005","journal-title":"Proc Int Conf Methods Tech Behav Res"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/SLT.2014.7078610"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"147","DOI":"10.21437\/Odyssey.2018-21","article-title":"Speaker diarization based on bayesian hmm with eigenvoice priors","author":"diez","year":"2018","journal-title":"Proc Odyssey 2018 The Speaker and Language Recognition Workshop"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP.2015.7178881"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICASSP.2018.8462665"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP.2018.8461375"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/JSTSP.2010.2081790"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP.2017.7953094"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TASL.2011.2125954"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref22","article-title":"A spectral clustering approach to speaker diarization","author":"ning","year":"2006","journal-title":"Ninth International Conference on Spoken Language Processing"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICASSP.2019.8683892"},{"year":"2012","author":"johnston","article-title":"WebRTC: APIs and RTCWEB protocols of the HTML5 real-time web","key":"ref24"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.21437\/Interspeech.2018-1742"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/TASL.2011.2158419"},{"year":"2019","article-title":"Local Voices Network","key":"ref25"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053122.pdf?arnumber=9053122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:28:10Z","timestamp":1656376090000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053122","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}