{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:40Z","timestamp":1775229820353,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383556","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T16:46:54Z","timestamp":1616690814000},"page":"897-904","source":"Crossref","is-referenced-by-count":54,"title":["Integration of Speech Separation, Diarization, and Recognition for Multi-Speaker Meetings: System Description, Comparison, and Analysis"],"prefix":"10.1109","author":[{"given":"Desh","family":"Raj","sequence":"first","affiliation":[]},{"given":"Pavel","family":"Denisov","sequence":"additional","affiliation":[]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Hakan","family":"Erdogan","sequence":"additional","affiliation":[]},{"given":"Zili","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Maokui","family":"He","sequence":"additional","affiliation":[]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Scott","family":"Wisdom","sequence":"additional","affiliation":[]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref33","article-title":"The Kaldi speech recog- Georg Stemmer, and Karel Vesely, nition toolkit","author":"povey","year":"2011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053760"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2813"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682556"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461974"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682274"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref11","article-title":"Pykaldi2: Yet another speech toolkit based on Kaldi and Py-Torch","author":"lu","year":"2019"},{"key":"ref12","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"cosentino","year":"2020","journal-title":"arXiv Audio and Speech Processing"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1085"},{"key":"ref14","article-title":"Investigation of end-to-end speaker-attributed ASR for continuous multi-talker recordings","author":"kanda","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/JSTSP.2019.2922820","article-title":"Speakerbeam: Speaker aware neural network for target speaker extraction in speech mixtures","volume":"13","author":"\u017emol\u00edkov\u00e1","year":"2019","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462081"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref4","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"MLMI"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref3","article-title":"Achieving human parity in conversational speech recognition","author":"xiong","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3088"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref5","article-title":"Observations on overlap: findings and implications for automatic processing of multi-party conversation","author":"shriberg","year":"2001","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1109\/SLT48900.2021.9383522","article-title":"Sequential multi-frame neural beamforming for speech separation and enhancement","author":"wang","year":"2021","journal-title":"Proc IEEE\/ACL Workshop Spoken Lang Technol (SLT)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003827"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref43","article-title":"Microsoft speaker diarization system for the voxceleb speaker recognition challenge 2020","author":"xiao","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"}],"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\/09383556.pdf?arnumber=9383556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T20:21:25Z","timestamp":1698092485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383556\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383556","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}