{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:22:58Z","timestamp":1778170978952,"version":"3.51.4"},"reference-count":132,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3393718","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T13:56:58Z","timestamp":1714053418000},"page":"2477-2493","source":"Crossref","is-referenced-by-count":94,"title":["CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7498-3773","authenticated-orcid":false,"given":"Sherif","family":"Abdulatif","sequence":"first","affiliation":[{"name":"Institute of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6397-2995","authenticated-orcid":false,"given":"Ruizhe","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8322-117X","authenticated-orcid":false,"given":"Bin","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17710"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0000000000000028"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2016-24"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref11","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746273"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref15","article-title":"Improved speech enhancement with the Wave-U-Net","author":"Macartney","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"ref19","article-title":"Multi-domain processing via hybrid denoising networks for speech enhancement","author":"Kim","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref21","article-title":"Universal speech enhancement with score-based diffusion","author":"Serr","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287606"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616267"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108499"},{"key":"ref28","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632794"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2908700"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1982.1163920"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.12.003"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2688"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462581"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2461"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743771"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1121\/1.408434"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.828896"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"issue":"4","key":"ref51","doi-asserted-by":"crossref","first-page":"3029","DOI":"10.1121\/1.4820893","article-title":"An algorithm to improve speech recognition in noise for hearing-impaired listeners","volume":"134","author":"Wang","year":"2013","journal-title":"J. Acoustical Soc. Amer."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55016-4_12"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.09.003"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2416653"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1629"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683231"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2870725"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3195112"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3079813"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1137"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1201\/9781315372150"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1121\/1.1570439"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/0022-460X(71)90392-0"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-596"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2290"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1121\/1.3631668"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6953357"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367221"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472934"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2536478"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-549"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953226"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2696307"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3155286"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553141"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2048"},{"key":"ref82","article-title":"Deep speech enhancement for reverberated and noisy signals using wide residual networks","author":"Ribas","year":"2019"},{"key":"ref83","first-page":"1","article-title":"The NTU-ADSC systems for reverberation challenge 2014","volume-title":"Proc. Reverberation Challenge Workshop","author":"Xiao","year":"2014"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref86","first-page":"53","article-title":"Bandwidth extension of audio signals by spectral band replication","volume-title":"Proc. IEEE Benelux Workshop Model Based Process. Coding Audio","author":"Ekstrand","year":"2002"},{"key":"ref87","first-page":"1","article-title":"Audio super-resolution using neural nets","volume-title":"Proc. Int. Conf. Learn. Representations (Workshop Track)","author":"Kuleshov","year":"2017"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462049"},{"key":"ref89","first-page":"1","article-title":"Temporal FiLM: Capturing long-range sequence dependencies with feature-wise modulations","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Birnbaum","year":"2019"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596082"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3054302"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11017"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TSP52935.2021.9522648"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2849578"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521347"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"ref97","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref103","first-page":"1","article-title":"The voice bank corpus: Design, collection and data analysis of a large regional accent speech database","volume-title":"Proc. Oriental Int. Conf. Speech Database Assessments","author":"Veaux","year":"2013"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1121\/1.4806631"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479278"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566470"},{"key":"ref107","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-582"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref110","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479814"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280459"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/49.601"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-350"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1978.1170567"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176347968"},{"key":"ref122","article-title":"Subjective test methodology for evaluating speech communication systems that include noise suppression algorithm","year":"2003"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171512"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683175"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054204"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414052"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3184889"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10508391.pdf?arnumber=10508391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T15:00:25Z","timestamp":1714748425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":132,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3393718","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.21187846.v1","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.21187846.v2","asserted-by":"object"}]},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}