{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:50:16Z","timestamp":1774965016203,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/lsp.2020.3040693","type":"journal-article","created":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T15:18:27Z","timestamp":1606490307000},"page":"2149-2153","source":"Crossref","is-referenced-by-count":73,"title":["WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-End Speech Enhancement"],"prefix":"10.1109","volume":"27","author":[{"given":"Tsun-An","family":"Hsieh","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-5071","authenticated-orcid":false,"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xugang","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-0418","authenticated-orcid":false,"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2968738"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.09.001"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937186"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1672"},{"key":"ref28","first-page":"1","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2628641"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683385"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2019.107019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1477"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2696307"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1773"},{"key":"ref25","first-page":"2743","article-title":"Coarse-to-fine optimization for speech enhancement","author":"yao","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref10","first-page":"53","article-title":"A family of MLP based nonlinear spectral estimators for noise reduction","author":"xie","year":"0","journal-title":"Proc ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953223"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref12","first-page":"2685","article-title":"Experiments on deep learning for speech denoising","author":"liu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-211"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref16","first-page":"22","article-title":"Recurrent neural networks for noise reduction in robust ASR","author":"maas","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.02.001"},{"key":"ref3","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"lu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2461"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2935803"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1121\/1.4806631"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref46","first-page":"550","article-title":"Residual networks behave like ensembles of relatively shallow networks","author":"veit","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1121\/1.4824632"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref47","article-title":"Batch normalization biases deep residual networks towards shallow paths","author":"de","year":"2020","journal-title":"CoRR"},{"key":"ref42","first-page":"1692","article-title":"Binary coding of speech spectrograms using a deep auto-encoder","author":"deng","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2604566"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref43","first-page":"27043","article-title":"DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM. NIST speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8966529\/09272838.pdf?arnumber=9272838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:56:46Z","timestamp":1641988606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9272838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/lsp.2020.3040693","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}