{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T15:00:58Z","timestamp":1776956458870,"version":"3.51.4"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413555","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7118-7122","source":"Crossref","is-referenced-by-count":22,"title":["Perceptual Loss Based Speech Denoising with an Ensemble of Audio Pattern Recognition and Self-Supervised Models"],"prefix":"10.1109","author":[{"given":"Saurabh","family":"Kataria","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Human Language Technology Center of Excellence,Baltimore,MD"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesus","family":"Villalba","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Human Language Technology Center of Excellence,Baltimore,MD"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Human Language Technology Center of Excellence,Baltimore,MD"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref12","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":"ref13","article-title":"Panns: Large-scale pretrained audio neural networks for audio pattern recognition","author":"kong","year":"2019","journal-title":"arXiv preprint arXiv 1912 10211"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref16","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref18","article-title":"Improved rawnet with filter-wise rescaling for text-independent speaker verification using raw waveforms","author":"jung","year":"2020","journal-title":"arXiv preprint arXiv 2004 06774"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2871419"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-66"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1191"},{"key":"ref5","article-title":"Sesqa: semi-supervised learning for speech quality assessment","author":"serr\u00e0","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref8","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"arXiv preprint arXiv 2006 10226"},{"key":"ref7","article-title":"Conformer: Convolution-augmented transformer for speech recognition","author":"gulati","year":"2020","journal-title":"arXiv preprint arXiv 2005 06138"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2143"},{"key":"ref9","article-title":"Multi-loss weighting with coefficient of variations","author":"groenendijk","year":"2020","journal-title":"arXiv preprint arXiv 2009 02026"},{"key":"ref1","article-title":"Speech denoising with deep feature losses","author":"germain","year":"2018","journal-title":"arXiv preprint arXiv 1806 10522"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1353"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref21","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"kendall","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref23","article-title":"Adapting auxiliary losses using gradient similarity","author":"du","year":"2018","journal-title":"arXiv preprint arXiv 1812 02588"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053214"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413555.pdf?arnumber=9413555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:21Z","timestamp":1659486021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413555","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}