{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T15:30:40Z","timestamp":1777390240703,"version":"3.51.4"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683828","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"6196-6200","source":"Crossref","is-referenced-by-count":24,"title":["Training Multi-task Adversarial Network for Extracting Noise-robust Speaker Embedding"],"prefix":"10.1109","author":[{"given":"Jianfeng","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Electronic Science and Technology, Xiamen University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Xiamen University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, Xiamen University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyang","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Xiamen University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"Media Coding Technology Lab, Huawei Media Technology Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingyin","family":"Xia","sequence":"additional","affiliation":[{"name":"Media Coding Technology Lab, Huawei Media Technology Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1680"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-883"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638976"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.899233"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23","author":"xu","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process (TASLP)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472647"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","article-title":"Speech enhancement with lstm recurrent neural networks and its application to noise-robust asr","author":"weninger","year":"2015","journal-title":"International Conference on Latent Variable Analysis and Signal Separation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref4","first-page":"4052","article-title":"Deep neural networks for small footprint text-dependent speaker verification","volume":"14","author":"variani","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2167240"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref7","article-title":"Deep speaker: an end-to-end neural speaker embedding system","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1705 02304"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683828.pdf?arnumber=8683828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:14:43Z","timestamp":1756754083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683828","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}