{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:18:55Z","timestamp":1780773535823,"version":"3.54.1"},"reference-count":34,"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"}],"funder":[{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414998","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6099-6103","source":"Crossref","is-referenced-by-count":27,"title":["Speaker Activity Driven Neural Speech Extraction"],"prefix":"10.1109","author":[{"given":"Marc","family":"Delcroix","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katerina","family":"Zmolikova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsubasa","family":"Ochiai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keisuke","family":"Kinoshita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","year":"0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref31","article-title":"Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis","author":"raj","year":"2021","journal-title":"SLT’21"},{"key":"ref30","first-page":"1462","article-title":"Performance measurement in blind audio source separation","volume":"14","author":"vincent","year":"2006","journal-title":"IEEE Trans ASLP"},{"key":"ref34","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref12","first-page":"i","article-title":"Voice activity detection using visual information","volume":"1","author":"liu","year":"2004","journal-title":"Proc ICASSP"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref14","first-page":"4930","article-title":"Speaker diarization using deep neural network embeddings","author":"garcia-romero","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref15","first-page":"6514","article-title":"Speaker diarization with region proposal network","author":"huang","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref17","article-title":"End-to-end neural diarization: Reformulating speaker diarization as simple multi-label classification","author":"fujita","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1249"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268910"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952163"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-667"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2266"},{"key":"ref29","year":"0"},{"key":"ref5","first-page":"307","article-title":"Deep extractor network for target speaker recovery from single channel speech mixtures","author":"chen","year":"2018","journal-title":"Proc of Interspeech’18"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1","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 on Graphics (TOG)"},{"key":"ref2","article-title":"TasNet: Surpassing ideal time-frequency masking for speech separation","author":"luo","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.117282"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660092"},{"key":"ref21","year":"0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288403"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.04.008"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081388"}],"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\/09414998.pdf?arnumber=9414998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:31:44Z","timestamp":1672129904000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414998\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414998","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}