{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:41:39Z","timestamp":1772300499763,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054311","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7294-7298","source":"Crossref","is-referenced-by-count":25,"title":["Speaker-Aware Target Speaker Enhancement by Jointly Learning with Speaker Embedding Extraction"],"prefix":"10.1109","author":[{"given":"Xuan","family":"Ji","sequence":"first","affiliation":[]},{"given":"Meng","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Chunlei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Xiaoyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref32","article-title":"Aishell-2: Transforming mandarin asr research into industrial scale","author":"du","year":"2018","journal-title":"arXiv 1808 10583"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1496"},{"key":"ref30","article-title":"End-to-end attention based text-dependent speaker verification","author":"zhang","year":"2016","journal-title":"SLT"},{"key":"ref35","first-page":"2579","article-title":"Visualizing high-dimensional data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1205"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref12","article-title":"Voicefilter: Targeted voice separation by speaker-conditioned spectrogram masking","author":"wang","year":"2018","journal-title":"arXiv preprint arXiv 1810 06008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682245"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1629"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref17","article-title":"Tasnet: Surpassing ideal time-frequency masking for speech separation","author":"luo","year":"2018","journal-title":"arXiv preprint arXiv 1809 07454"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1608","article-title":"End-to-end text-independent speaker verification with triplet loss on short utterances","author":"zhang","year":"2017","journal-title":"ISCA INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2831456"},{"key":"ref28","article-title":"Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks","author":"chen","year":"2015","journal-title":"InterSpeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2881912"},{"key":"ref29","article-title":"Modeling speaker variability using long short-term memory networks for speech recognition","author":"li","year":"2015","journal-title":"InterSpeech"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1668"},{"key":"ref8","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 Transactions on Graphics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2266"},{"key":"ref2","first-page":"31","article-title":"Deep clustering: Discriminative embeddings for segmentation and separation","author":"hershey","year":"2016","journal-title":"The Proceedings of ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2713"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682749"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683097"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054311.pdf?arnumber=9054311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:09:24Z","timestamp":1656374964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054311","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}