{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T07:34:30Z","timestamp":1762068870832,"version":"build-2065373602"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892355","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-10","source":"Crossref","is-referenced-by-count":7,"title":["Two-Stage Deep Learning Approach for Speech Enhancement and Reconstruction in The Frequency and Time Domains"],"prefix":"10.1109","author":[{"given":"Soha A.","family":"Nossier","sequence":"first","affiliation":[{"name":"University of East London,Dept. of Engineering and Computing,London,UK"}]},{"given":"Julie","family":"Wall","sequence":"additional","affiliation":[{"name":"University of East London,Dept. of Engineering and Computing,London,UK"}]},{"given":"Mansour","family":"Moniri","sequence":"additional","affiliation":[{"name":"University of East London,Dept. of Engineering and Computing,London,UK"}]},{"given":"Cornelius","family":"Glackin","sequence":"additional","affiliation":[{"name":"Intelligent Voice Ltd,London,UK"}]},{"given":"Nigel","family":"Cannings","sequence":"additional","affiliation":[{"name":"Intelligent Voice Ltd,London,UK"}]}],"member":"263","reference":[{"journal-title":"TopCoder","article-title":"176 spoken languages","year":"2017","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2968738"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2020.107398"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206623"},{"key":"ref37","article-title":"Noisy speech database for training speech enhancement algorithms and tts models","author":"valentini-botinhao","year":"2017","journal-title":"University of Edinburg"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref35","first-page":"5206","article-title":"Librispeech: an ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP IEEE"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-168"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1109\/TASLP.2018.2870725","article-title":"Two-stage deep learning for noisyreverberant speech enhancement","volume":"27","author":"zhao","year":"0","journal-title":"Trans Audio Speech Lang Proc"},{"key":"ref27","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"0","journal-title":"Int Conf Learning Rep (ICLR)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472934"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1982.1163920"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1495"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3016487"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937222"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.06.002"},{"key":"ref51","first-page":"2031","article-title":"Metricgan: Generative adversarial networks based black-box metric scores optimization for speech enhancement","author":"fu","year":"0","journal-title":"Int Conf Mach Learn"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987441"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053214"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054254"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053188"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1609"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","article-title":"On training targets for supervised speech separation","volume":"22","author":"wang","year":"0","journal-title":"Trans Audio Speech Lang Proc"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1223"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206928"},{"key":"ref17","first-page":"3291","author":"d\u00e9fossez","year":"2020","journal-title":"Real time speech enhancement in the waveform domain"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178800"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414721"},{"key":"ref4","first-page":"1109","article-title":"Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator","volume":"32","author":"malah","year":"0","journal-title":"IEEE Trans Acoustics Speech and Sig Proc"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319311"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.12.006"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10010017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref47","article-title":"Improved speech enhancement with the wave-u-net","author":"macartney","year":"2018","journal-title":"ArXiv"},{"key":"ref42","article-title":"Reverberant speech database for training speech dereverberation algorithms and tts models","author":"valentini-botinhao","year":"2016","journal-title":"University of Edinburg"},{"key":"ref41","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning Toolkit (version 0.92)","author":"yamagishi","year":"2019","journal-title":"University of Edinburg"},{"key":"ref44","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":"rix","year":"2001","journal-title":"ITU-T Recommendation"},{"journal-title":"100 nonspeech environmental sounds","year":"2014","author":"hu","key":"ref43"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892355.pdf?arnumber=9892355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:00:21Z","timestamp":1667516421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892355","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}