{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T01:09:58Z","timestamp":1784077798385,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000055","name":"NIDCD","doi-asserted-by":"publisher","award":["R01 DC012048"],"award-info":[{"award-number":["R01 DC012048"]}],"id":[{"id":"10.13039\/100000055","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000055","name":"NIDCD","doi-asserted-by":"publisher","award":["R01 DC015521"],"award-info":[{"award-number":["R01 DC015521"]}],"id":[{"id":"10.13039\/100000055","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ohio Supercomputer Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1109\/taslp.2018.2876171","type":"journal-article","created":{"date-parts":[[2018,10,15]],"date-time":"2018-10-15T18:30:28Z","timestamp":1539628228000},"page":"189-198","source":"Crossref","is-referenced-by-count":164,"title":["Gated Residual Networks With Dilated Convolutions for Monaural Speech Enhancement"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5073-8060","authenticated-orcid":false,"given":"Ke","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6084-043X","authenticated-orcid":false,"given":"Jitong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8195-6319","authenticated-orcid":false,"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-22794-6_12"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2017.8096126"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref32","article-title":"Dense prediction on sequences with time-dilated convolutions for speech recognition","author":"sercu","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref36","first-page":"4790","article-title":"Conditional image generation with pixelcnn\n decoders","author":"van den oord","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461819"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref27","first-page":"1310","article-title":"On the\n difficulty of training recurrent neural networks","author":"pascanu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.4324\/9781410604255","author":"plomp","year":"2001","journal-title":"The Intelligent Ear On the Nature of Sound Perception"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.4986931"},{"key":"ref1","first-page":"258","article-title":"Monoaural audio source separation\n using deep convolutional neural networks","author":"chandna","year":"0","journal-title":"Proc Int Conf Latent Variable Anal Signal Separat"},{"key":"ref20","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref21","first-page":"323","article-title":"Singing voice separation with deep u-net convolutional networks","author":"jansson","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ECMSM.2017.7945915"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2628641"},{"key":"ref26","article-title":"A fully convolutional neural network for speech enhancement","author":"park","year":"2016"},{"key":"ref25","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"lu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref10","article-title":"End-to-end waveform utterance enhancement\n for direct evaluation metrics optimization by fully convolutional neural networks","author":"fu","year":"2017"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/APSIPA.2017.8281993","article-title":"Raw waveform-based speech enhancement by\n fully convolutional networks","author":"fu","year":"2017"},{"key":"ref40","author":"wang","year":"2006","journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"ref13","first-page":"315","article-title":"Deep sparse\n rectifier neural networks","author":"glorot","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2017.8309164"},{"key":"ref15","first-page":"340","article-title":"Multi-resolution fully convolutional\n neural networks for monaural audio source separation","author":"grais","year":"0","journal-title":"Proc Int Conf Latent Variable Anal Signal Separat"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854479"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2015.7394335"},{"key":"ref4","article-title":"Semantic image segmentation with deep convolutional nets and full\n connected CRFs","author":"chen","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref6","first-page":"933","article-title":"Language modeling with gated\n convolutional networks","volume":"70","author":"dauphin","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref5","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"clevert","year":"2015"},{"key":"ref8","first-page":"1","article-title":"Complex spectrogram enhancement by\n convolutional neural network with multi-metrics learning","author":"fu","year":"0","journal-title":"Proc IEEE 27th Int Workshop Mach Learn Signal Process"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref49","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref9","first-page":"3768","article-title":"SNR-aware\n convolutional neural network modeling for speech enhancement","author":"fu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854294"},{"key":"ref45","first-page":"91","article-title":"Speech enhancement with LSTM recurrent neural\n networks and its application to noise-robust ASR","author":"weninger","year":"0","journal-title":"Proc Int Conf Latent Variable Anal Signal Separat"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref42","article-title":"Understanding convolution for semantic\n segmentation","author":"wang","year":"2017"},{"key":"ref41","article-title":"Supervised speech separation based on deep learning: an overview","author":"wang","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8471003\/08492428.pdf?arnumber=8492428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:13:26Z","timestamp":1657746806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8492428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":50,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2876171","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1]]}}}