{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T13:40:43Z","timestamp":1769348443865,"version":"3.49.0"},"reference-count":45,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383602","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"582-589","source":"Crossref","is-referenced-by-count":23,"title":["Multi-Class Spectral Clustering with Overlaps for Speaker Diarization"],"prefix":"10.1109","author":[{"given":"Desh","family":"Raj","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zili","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref38","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053982"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2813"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017"},{"key":"ref10","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":"ref40","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-566","article-title":"A spectral clustering approach to speaker diarization","author":"ning","year":"2006","journal-title":"InterSpeech"},{"key":"ref11","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":"ref12","article-title":"Detecting overlapping speech with long short-term memory recurrent neural networks","author":"geiger","year":"2013","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-188","article-title":"Detecting overlapped speech on short timeframes using deep learning","author":"andrei","year":"2017","journal-title":"InterSpeech"},{"key":"ref14","article-title":"Enhancing LSTM RNN-based speech overlap detection by artificially mixed data","author":"hagerer","year":"2017","journal-title":"Semantic Audio"},{"key":"ref15","article-title":"Detection of overlapping speech for the purposes of speaker diarization","author":"kunesov\u00e1","year":"2019","journal-title":"SPECOM"},{"key":"ref16","article-title":"Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detection","author":"bullock","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-21"},{"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","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"InterSpeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1742"},{"key":"ref27","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":"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","article-title":"The ami meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"MLMI"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178881"},{"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":"publisher","DOI":"10.1109\/ICASSP.2008.4518619"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238361"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref42","article-title":"On the use of agglomerative and spectral clustering in speaker diarization of meetings","author":"luque","year":"2012","journal-title":"Odyssey"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21136\/CMJ.1973.101168"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2042121"},{"key":"ref23","article-title":"Matrix perturbation theory","author":"stewart","year":"1990"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178329"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-163","article-title":"On the use of spectral and iterative methods for speaker diarization","author":"shum","year":"2012","journal-title":"InterSpeech"},{"key":"ref25","article-title":"On spectral clustering: Analysis and an algorithm","author":"ng","year":"2001","journal-title":"NIPS"}],"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\/09383602.pdf?arnumber=9383602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T00:22:12Z","timestamp":1698106932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383602","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}