{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:19:41Z","timestamp":1781713181796,"version":"3.54.5"},"reference-count":45,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100004318","name":"Microsoft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008238","name":"Hitachi","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008238","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383490","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"881-888","source":"Crossref","is-referenced-by-count":37,"title":["DOVER-Lap: A Method for Combining Overlap-Aware Diarization Outputs"],"prefix":"10.1109","author":[{"given":"Desh","family":"Raj","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leibny","family":"Paola Garcia-Perera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zili","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Povey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Stolcke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Multi-class spectral clustering with overlaps for speaker diarization","author":"raj","year":"2021","journal-title":"IEEE Spoken Language Technology Workshop"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68279-0_8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2006.05.004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref30","article-title":"Microsoft speaker diarization system for the VoxCeleb speaker recognition challenge 2020","author":"xiao","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref35","article-title":"Complexity and approximation: combinatorial optimization problems and their approximability properties","author":"ausiello","year":"1999"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(91)90246-E"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-165","article-title":"Speaker diarization of overlapping speech based on silence distribution in meeting recordings","author":"yella","year":"2012","journal-title":"InterSpeech"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2918706"},{"key":"ref11","article-title":"Detecting overlapping speech with long short-term memory recurrent neural networks","author":"geiger","year":"2013","journal-title":"InterSpeech"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-188"},{"key":"ref13","article-title":"Enhancing LSTM RNN-based speech overlap detection by artificially mixed data","author":"hagerer","year":"2017","journal-title":"Semantic Audio"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-26061-3_26"},{"key":"ref15","article-title":"Overlap-aware diarization: resegmentation using neural end-toend overlapped speech detection","author":"bullock","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-21"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178881"},{"key":"ref18","article-title":"End-to-end neural diarization: Reformulating speaker diarization as simple multi-label classification","author":"fujita","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053760"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1742"},{"key":"ref27","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"MLMI"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref6","first-page":"4052","article-title":"Deep neural networks for small footprint text-dependent speaker verification","author":"variani","year":"2014","journal-title":"ICASSP"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.21437\/CHiME.2020-1","article-title":"CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings","author":"watanabe","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518619"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-326","article-title":"Speech overlap detection in a two-pass speaker diarization system","author":"huijbregts","year":"2009","journal-title":"InterSpeech"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","article-title":"Speaker diarization: A review of recent research","volume":"20","author":"mir\u00f3","year":"2012","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref20","article-title":"Targetspeaker voice activity detection: a novel approach for multispeaker diarization in a dinner party scenario","author":"medennikov","year":"2020"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TASL.2007.902460","article-title":"Acoustic beamforming for speaker diarization of meetings","volume":"15","author":"mir\u00f3","year":"2007","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-009-9124-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3088"},{"key":"ref24","article-title":"The SRI March 2000 Hub-5 conversational speech transcription system","author":"stolcke","year":"2000","journal-title":"Proc NIST Speech Transcription Workshop"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366923"},{"key":"ref23","article-title":"Posterior probability decoding, confidence estimation and system combination","author":"evermann","year":"2000","journal-title":"Proc NIST Speech Transcription Workshop"},{"key":"ref44","article-title":"NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing","author":"drude","year":"2018","journal-title":"10 ITG Symposium on Speech Communication"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004031"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21437\/CHiME.2020-11","article-title":"The JHU multi-microphone multi-speaker ASR system for the CHiME-6 challenge","author":"arora","year":"2020"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383490.pdf?arnumber=9383490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T13:16:46Z","timestamp":1671715006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383490","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}