{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T18:03:49Z","timestamp":1773511429289,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414677","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"11-15","source":"Crossref","is-referenced-by-count":10,"title":["Count And Separate: Incorporating Speaker Counting For Continuous Speaker Separation"],"prefix":"10.1109","author":[{"given":"Zhong-Qiu","family":"Wang","sequence":"first","affiliation":[]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201357","article-title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","volume":"37","author":"ephrat","year":"2018","journal-title":"ACM Trans Graph"},{"key":"ref12","article-title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","author":"zeghidour","year":"2020"},{"key":"ref13","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":"ref14","article-title":"Continuous Speech Separation with Conformer","author":"chen","year":"0"},{"key":"ref15","article-title":"Multi-Microphone Complex Spectral Mapping for Utterance-Wise and Continuous Speaker Separation","author":"wang","year":"2020"},{"key":"ref16","first-page":"241","article-title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","author":"yu","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2975902"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref4","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":"ref3","first-page":"1","article-title":"Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation","author":"wang","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref6","first-page":"7319","article-title":"Enhancing End-to-End Multi-Channel Speech Separation Via Spatial Feature Learning","author":"gu","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2881912"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref7","first-page":"71","article-title":"Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective","author":"wang","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref1","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"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref20","article-title":"Room Impulse Response Generator","author":"habets","year":"2010"},{"key":"ref22","author":"manohar","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414677.pdf?arnumber=9414677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:41:02Z","timestamp":1652182862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414677\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414677","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}