{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T01:10:18Z","timestamp":1773277818275,"version":"3.50.1"},"reference-count":24,"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\/icassp40776.2020.9053521","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7289-7293","source":"Crossref","is-referenced-by-count":11,"title":["The Sound of My Voice: Speaker Representation Loss for Target Voice Separation"],"prefix":"10.1109","author":[{"given":"Seongkyu","family":"Mun","sequence":"first","affiliation":[]},{"given":"Soyeon","family":"Choe","sequence":"additional","affiliation":[]},{"given":"Jaesung","family":"Huh","sequence":"additional","affiliation":[]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref12","first-page":"5554","article-title":"Single channel target speaker extraction and recognition with speaker beam","author":"marc","year":"2018","journal-title":"IEEE ICASSP 2018"},{"key":"ref13","first-page":"8","article-title":"Learning speaker representation for neural network based multichannel speaker extraction","author":"\u017emol\u00edkov\u00e1","year":"2017","journal-title":"2017 IEEE ASRU"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1205"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref18","first-page":"1335","article-title":"Person re-identification by multichannel parts-based cnn with improved triplet loss function","author":"cheng","year":"2016","journal-title":"Proc CVPR"},{"key":"ref19","article-title":"Superseded - cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"veaux","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461711"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.168"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref2","first-page":"2234","article-title":"Improved techniques for training gans","author":"salimans","year":"2016","journal-title":"NIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref22","first-page":"749","article-title":"Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs","volume":"2","author":"antony","year":"2001","journal-title":"Proc ICASSP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1496"},{"key":"ref23","article-title":"Speaker-aware deep denoising autoencoder with embedded speaker identity for speech enhancement","author":"fu-kai","year":"2019","journal-title":"InterSpeech"}],"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\/09053521.pdf?arnumber=9053521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:27:00Z","timestamp":1656376020000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053521\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053521","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}