{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:09:02Z","timestamp":1776110942108,"version":"3.50.1"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688198","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"996-1002","source":"Crossref","is-referenced-by-count":14,"title":["3D Spatial Features for Multi-Channel Target Speech Separation"],"prefix":"10.1109","author":[{"given":"Rongzhi","family":"Gu","sequence":"first","affiliation":[{"name":"Peking University,Shenzhen,China"}]},{"given":"Shi-Xiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,USA"}]},{"given":"Meng","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,USA"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,USA"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682470"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047270"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-018-9650-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2876169"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","article-title":"Conv-tasnet: Surpassing ideal time-frequency magnitude masking for speech separation","volume":"27","author":"yi","year":"2019","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3181"},{"key":"ref18","first-page":"241","article-title":"Permutation invariant training of deep mod-elsfor speaker-independent multi-talker speech separation","author":"dong","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639593"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref6","first-page":"4290","article-title":"Neural spatial filter: Target speaker speech separation assisted with directional information","author":"rongzhi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2881912"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cock-tail party: a speaker-independent audio-visual model for speech separation","volume":"37","author":"ephrat","year":"2018","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref2","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 Pro-cessing"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159","article-title":"Supervised speech separation based on deep learning: An overview","volume":"26","author":"deliang","year":"2018","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1109\/JSTSP.2020.2980956","article-title":"Multi-modal multi-channel target speech separation","volume":"14","author":"rongzhi","year":"2020","journal-title":"IEEE Journal of Se-lected Topics in Signal Processing"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688198.pdf?arnumber=9688198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:58:27Z","timestamp":1652201907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688198\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688198","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}