{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:24:43Z","timestamp":1772119483356,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013290","name":"National Key Research and Development Program of China Stem Cell and Translational Research","doi-asserted-by":"publisher","award":["2020YFC2004104"],"award-info":[{"award-number":["2020YFC2004104"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11911540067"],"award-info":[{"award-number":["11911540067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/lsp.2021.3113604","type":"journal-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T20:10:29Z","timestamp":1632168629000},"page":"1958-1962","source":"Crossref","is-referenced-by-count":15,"title":["FSCNet: Feature-Specific Convolution Neural Network for Real-Time Speech Enhancement"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0635-1480","authenticated-orcid":false,"given":"Longbiao","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6272-9169","authenticated-orcid":false,"given":"Junfeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6907-5770","authenticated-orcid":false,"given":"Yonghong","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref30","article-title":"Noisy speech database for training speech enhancement algorithms and TTS models","author":"valentini-botinhao","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3040693"},{"key":"ref36","first-page":"7098","article-title":"TSTNN: Two-stage transformer based neural network for speech enhancement in the time domain","author":"wang","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref35","first-page":"9458","article-title":"Phasen: A phase-and-harmonics-aware speech enhancement network","volume":"34","author":"yin","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref34","article-title":"Exploring the best loss function for DNN-based low-latency speech enhancement with temporal convolutional networks","author":"koyama","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref11","first-page":"3274","article-title":"Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks","author":"chen","year":"0","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2018.8547084"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref17","first-page":"1829","article-title":"Two heads are better than one: A two-stage complex spectral mapping approach for monaural speech enhancement","volume":"29","author":"li","year":"2021","journal-title":"IEEE Transactions on Audio"},{"key":"ref18","first-page":"4790","article-title":"Conditional image generation with PixelCNN decoders","author":"oord","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2561"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref9","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","volume":"2013","author":"lu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107511"},{"key":"ref21","first-page":"6648","article-title":"Monaural speech enhancement with complex convolutional block attention module and joint time frequency losses","author":"zhao","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"ref23","first-page":"12321","article-title":"Involution: Inverting the inherence of convolution for visual recognition","author":"li","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref25","article-title":"Layer normalization","author":"hinton","year":"2016"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9325893\/09540980.pdf?arnumber=9540980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:35Z","timestamp":1652194235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9540980\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/lsp.2021.3113604","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}