{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:38:52Z","timestamp":1774021132319,"version":"3.50.1"},"reference-count":23,"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\/icassp40776.2020.9053110","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7584-7588","source":"Crossref","is-referenced-by-count":23,"title":["Feature Enhancement with Deep Feature Losses for Speaker Verification"],"prefix":"10.1109","author":[{"given":"Saurabh","family":"Kataria","sequence":"first","affiliation":[]},{"given":"Phani Sankar","family":"Nidadavolu","sequence":"additional","affiliation":[]},{"given":"Jesus","family":"Villalba","sequence":"additional","affiliation":[]},{"given":"Nanxin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Paola","family":"Garcia-Perera","sequence":"additional","affiliation":[]},{"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"hu","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003748"},{"key":"ref12","article-title":"Unsupervised feature enhancement for speaker verification","author":"nidadavolu","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683055"},{"key":"ref14","article-title":"Swish: a self-gated activation function","volume":"7","author":"ramachandran","year":"2017"},{"key":"ref15","article-title":"The jhu-mit system description for nist sre18","author":"villalba","year":"2018","journal-title":"Tech Rep"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2979"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref18","article-title":"Robust signal-to-noise ratio estimation based on waveform amplitude distribution analysis","author":"kim","year":"2008","journal-title":"Ninth Annual Conference of the International Speech Communication Association"},{"key":"ref19","article-title":"Mu-san: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref4","article-title":"Speech denoising with deep feature losses","author":"germain","year":"2018"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"Segan: Speech enhancement generative adversarial network","author":"pascual","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1496"},{"key":"ref5","first-page":"101026","article-title":"State-of-the-art speaker recognition with neural network embeddings in nist sre18 and speakers in the wild evaluations","author":"villalba","year":"2019","journal-title":"Computer Speech & Language"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2961"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1620","article-title":"Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification","author":"michelsanti","year":"2017"},{"key":"ref2","article-title":"The voices from a distance challenge 2019 evaluation plan","author":"nandwana","year":"2019"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952151"},{"key":"ref9","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"johnson","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1055\/s-0036-1580745","article-title":"Homebank: An online repository of daylong child-centered audio recordings","volume":"37","author":"vandam","year":"2016","journal-title":"Seminars in Speech and Language"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref23","article-title":"Speaker detection in the wild: lessons learned from jsalt 2019","author":"garcia","year":"2020","journal-title":"ICASSP"}],"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\/09053110.pdf?arnumber=9053110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:10:28Z","timestamp":1656375028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053110","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}