{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:06:54Z","timestamp":1740100014495,"version":"3.37.3"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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"}],"funder":[{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414695","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"671-675","source":"Crossref","is-referenced-by-count":1,"title":["Speech Enhancement Autoencoder with Hierarchical Latent Structure"],"prefix":"10.1109","author":[{"given":"Koen","family":"Oostermeijer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Frequency gating: Improved convolutional neural networks for speech enhancement in the time-frequency domain","author":"oostermeijer","year":"2020","journal-title":"Annual Summit and Conference 2020 Asia-Pacific Signal and Information Processing Association"},{"article-title":"On the variance of the adaptive learning rate and beyond","year":"2019","author":"liu","key":"ref32"},{"key":"ref31","article-title":"Demand: a collection of multi-channel recordings of acoustic noise in diverse environments","author":"thiemann","year":"2013","journal-title":"Supported by Inria under the Associate Team Program VERSAMUS"},{"key":"ref30","article-title":"Csr-i (wsj0) complete","author":"garofalo","year":"2007","journal-title":"Linguistic Data Consortium"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461861"},{"key":"ref36","article-title":"Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","author":"recommendation","year":"2001","journal-title":"ITU-T Rec P 862"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196643"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326090"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638983"},{"key":"ref15","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"},{"article-title":"A fully convolutional neural network for speech enhancement","year":"2016","author":"park","key":"ref16"},{"key":"ref17","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","volume":"2013","author":"lu","year":"2013","journal-title":"InterSpeech"},{"key":"ref18","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"howard","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2016.11.012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"article-title":"Speech enhancement for cochlear implants","year":"2014","author":"koning","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref29","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1109\/TSA.2003.814458","article-title":"A generalized subspace approach for enhancing speech corrupted by colored noise","volume":"11","author":"hu","year":"2003","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1852873"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518538"},{"key":"ref1","article-title":"Method and apparatus for multi-sensory speech enhancement on a mobile device","author":"granovetter","year":"2007","journal-title":"US Patent"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1284"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"Segan: Speech enhancement generative adversarial network","author":"pascual","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.12.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2871419"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462581"},{"article-title":"Nvae: A deep hierarchical variational autoencoder","year":"2020","author":"vahdat","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2953810"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","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\/09414695.pdf?arnumber=9414695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:03Z","timestamp":1652197263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414695\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414695","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}