{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:58:35Z","timestamp":1780588715301,"version":"3.54.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Telkom University Research Grant"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3290908","type":"journal-article","created":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T17:27:38Z","timestamp":1688059658000},"page":"66979-66994","source":"Crossref","is-referenced-by-count":27,"title":["NSE-CATNet: Deep Neural Speech Enhancement Using Convolutional Attention Transformer Network"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0010-0629","authenticated-orcid":false,"given":"Nasir","family":"Saleem","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Faculty of Engineering and Technology, Gomal University, Dera Ismail Khan, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3345-4669","authenticated-orcid":false,"given":"Teddy Surya","family":"Gunawan","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3686-3575","authenticated-orcid":false,"given":"Mira","family":"Kartiwi","sequence":"additional","affiliation":[{"name":"Information Systems Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bambang Setia","family":"Nugroho","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Telkom University, Bandung, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Inung","family":"Wijayanto","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Telkom University, Bandung, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2868407"},{"key":"ref57","first-page":"764","article-title":"An integrated CNN-GRU framework for complex ratio mask estimation in speech enhancement","author":"hasannezhad","year":"2020","journal-title":"Proc Asia–Pacific Signal Inf Process Assoc Annu Summit Conf (APSIPA ASC)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CISP.2011.6100732"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2631"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3021061"},{"key":"ref55","first-page":"755","article-title":"Perceptual evaluation of speech quality (PESQ) the new ITU standard for end-to-end speech quality assessment part I—Time-delay compensation","volume":"50","author":"rix","year":"2002","journal-title":"J Audio Eng Soc"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2911401"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953125"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-190047"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.9781\/ijimai.2019.06.001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.32604\/iasc.2023.028090"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3236242"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref50","article-title":"Description of the RSG-10 noise database","author":"steeneken","year":"1988"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-46"},{"key":"ref45","first-page":"641","article-title":"A comparison of transformer and recurrent neural networks on multilingual neural machine translation","author":"lakew","year":"2018","journal-title":"Proc 27th Int Conf Comput Linguistics"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-774"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3225649"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413580"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref43","article-title":"Noisy speech database for training speech enhancement algorithms and TTS models","author":"valentini","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-023-10020-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2023.01.011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3253719"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/s22207782"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107347"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462155"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.05.017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287618"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107647"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS50536.2020.9310011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-022-10039-y"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3040693"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3039600"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref24","article-title":"CMGAN: Conformer-based metric-GAN for monaural speech enhancement","author":"abdulatif","year":"2022","journal-title":"arXiv 2209 11112"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6377"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108499"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632794"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2015.03.008"},{"key":"ref64","first-page":"225","article-title":"IEEE recommended practice for speech quality measurements","volume":"ae 17","author":"rothauser","year":"1969","journal-title":"IEEE Trans Audio Electroacoust"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3079813"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107914"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1121\/10.0003321"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-021-08313-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054230"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987441"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659692"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10168245.pdf?arnumber=10168245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T18:19:50Z","timestamp":1690913990000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10168245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3290908","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}