{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:18:56Z","timestamp":1780773536832,"version":"3.54.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746896","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"281-285","source":"Crossref","is-referenced-by-count":9,"title":["Localization based Sequential Grouping for Continuous Speech Separation"],"prefix":"10.1109","author":[{"given":"Zhong-Qiu","family":"Wang","sequence":"first","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Ohio State University,Department of Computer Science and Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"5739","article-title":"Multi-Microphone Neural Speech Separation for Far-Field Multi-Talker Speech Recognition","author":"yoshioka","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref38","article-title":"Continuous Speech Separation with Conformer","author":"chen","year":"2020"},{"key":"ref33","article-title":"Multi-Microphone Complex Spectral Mapping for Utterance-Wise and Continuous Speaker Separation","author":"wang","year":"2020"},{"key":"ref32","first-page":"6125","article-title":"Robust Direction Estimation with Convolutional Neural Networks Based Steered Response Power","author":"pertil\u00e4","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1778","DOI":"10.1109\/TASLP.2020.2998279","article-title":"Complex Spectral Mapping for Single- and Multi-Channel Speech Enhancement and Robust ASR","volume":"28","author":"wang","year":"2020","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2975902"},{"key":"ref37","author":"manohar","year":"2018"},{"key":"ref36","article-title":"Room Impulse Response Generator","author":"habets","year":"2010"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04619-7_8"},{"key":"ref34","first-page":"486","article-title":"Multi-Microphone Complex Spectral Mapping for Speech Dereverberation","author":"wang","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref40","first-page":"5329","article-title":"X-Vectors: Robust DNN Embeddings for Speaker Recognition","volume":"2018 april","author":"snyder","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003827"},{"key":"ref12","article-title":"All-Neural Online Source Separation, Counting, and Diarization for Meeting Analysis","author":"von neumann","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref13","article-title":"Tackling Real Noisy Reverberant Meetings with All-Neural Source Separation, Counting, and Diarization System","author":"kinoshita","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref14","first-page":"7284","article-title":"Continuous Speech Separation: Dataset and Analysis","author":"chen","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383522"},{"key":"ref17","article-title":"Microsoft Speaker Diarization System for The VoxCeleb Speaker Recognition Challenge 2020","author":"xiao","year":"2021","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref18","first-page":"176","article-title":"Location Based Speaker Segmentation","author":"lathoud","year":"2003","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref19","first-page":"112","article-title":"Speaker Turn Segmentation Based on Between-Channel Differences","author":"ellis","year":"2004","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref28","article-title":"Multi-Channel Multi-Frame ADL-MVDR for Target Speech Separation","author":"zhang","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref3","first-page":"6301","article-title":"Fully Supervised Speaker Diarization","author":"zhang","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref6","article-title":"Speaker Diarization with Region Proposal Network","author":"huang","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref29","article-title":"End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend","author":"zhang","year":"2021","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref5","article-title":"End-to-End Speaker Diarization as Post-Processing","author":"horiguchi","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref2","article-title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","author":"park","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"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":"anguera","year":"2012","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref20","first-page":"605","article-title":"Clustering and Segmenting Speakers and Their Locations in Meetings","author":"ajmera","year":"2004","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700890"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2876169"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref25","first-page":"31","article-title":"Deep Clustering: Discriminative Embeddings for Segmentation and Separation","author":"hershey","year":"2016","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746896.pdf?arnumber=9746896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:09:26Z","timestamp":1660594166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746896\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746896","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}