{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T06:38:49Z","timestamp":1775716729832,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003983","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T02:01:33Z","timestamp":1582250493000},"page":"667-673","source":"Crossref","is-referenced-by-count":86,"title":["Time Domain Audio Visual Speech Separation"],"prefix":"10.1109","author":[{"given":"Jian","family":"Wu","sequence":"first","affiliation":[]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Shi-Xiong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Lian-Wu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Meng","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","author":"diederik","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref11","article-title":"Deep audiovisual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref12","author":"brendan","year":"2018","journal-title":"Large-scale visual speech recognition"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref15","author":"afouras","year":"2018","journal-title":"The conversation Deep audio-visual speech enhancement"},{"key":"ref16","author":"ariel","year":"2018","journal-title":"Looking to listen at the cocktail party A speaker-independent audiovisual model for speech separation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref18","author":"stafylakis","year":"2017","journal-title":"Com-bining residual networks with lstms for lipreading"},{"key":"ref19","author":"wang","year":"2018","journal-title":"End-to-end speech separation with unfolded iterative phase reconstruction"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref27","author":"ioffe","year":"2015","journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"2655","DOI":"10.21437\/Interspeech.2017-667","article-title":"Speaker-aware neural network based beamformer for speaker extraction in speech mixtures","author":"zmolikova","year":"2017","journal-title":"InterSpeech"},{"key":"ref29","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Technical Report of IEICE Signal Processing Society"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref8","author":"quan","year":"2018","journal-title":"Voicefilter Targeted voice separation by speaker-conditioned spectrogram masking"},{"key":"ref7","author":"wang","year":"2018","journal-title":"Deep extractor network for target speaker recovery from single channel speech mixtures"},{"key":"ref2","first-page":"31","article-title":"Deep clustering: Discriminative em-beddings for segmentation and separation","author":"john","year":"2016","journal-title":"2016 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","article-title":"Complex ratio masking for monaural speech separation","volume":"24","author":"donald","year":"2016","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process (TASLP)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683231"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2904183"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref23","first-page":"708","article-title":"Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks","author":"hakan","year":"2015","journal-title":"2015 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"SG, Singapore","start":{"date-parts":[[2019,12,14]]},"end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003983.pdf?arnumber=9003983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:51:20Z","timestamp":1658141480000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003983","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}