{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T22:04:17Z","timestamp":1778537057028,"version":"3.51.4"},"reference-count":85,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1109\/taslp.2023.3318965","type":"journal-article","created":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:34:24Z","timestamp":1695666864000},"page":"3390-3403","source":"Crossref","is-referenced-by-count":20,"title":["Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environments"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4965-3514","authenticated-orcid":false,"given":"Philippe","family":"Gonzalez","sequence":"first","affiliation":[{"name":"Department of Health Technology, Technical University of Denmark, Lyngby, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0941-3146","authenticated-orcid":false,"given":"Tommy Sonne","family":"Alstr\u00f8m","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5463-5509","authenticated-orcid":false,"given":"Tobias","family":"May","sequence":"additional","affiliation":[{"name":"Department of Health Technology, Technical University of Denmark, Lyngby, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00858"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.4901133"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1121\/1.4789895"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196924"},{"key":"ref58","first-page":"22405","article-title":"SWAD: Domain generalization by seeking flat minima","author":"cha","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref53","author":"murphy","year":"2022","journal-title":"Probabilistic Machine Learning An introduction"},{"key":"ref52","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref11","first-page":"224","article-title":"Cocktail party processing via structured prediction","author":"wang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2193391"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3016487"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1121\/1.4986931"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2215596"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref50","year":"2001","journal-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"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4780815"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2051354"},{"key":"ref48","article-title":"Simulated room impulse responses","year":"0"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107867"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3109\/00206090109073110"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.2589280"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3813\/AAA.919349"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2020.0026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3109\/14992027.2012.658972"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.2403.375"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.02.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.387773"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.1002.186"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.4789891"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.3559683"},{"key":"ref82","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref80","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proc IEEE Eur Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-686"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref75","first-page":"1","article-title":"Deep complex networks","author":"trabelsi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","article-title":"A tandem algorithm for pitch estimation and voiced speech segregation","volume":"18","author":"hu","year":"2010","journal-title":"IEEE Audio Speech Lang Process"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref33","first-page":"357","article-title":"The design for the wall street journal-based CSR corpus","author":"paul","year":"0","journal-title":"Proc Workshop Speech Natural Lang"},{"key":"ref77","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":"ref32","article-title":"Akustiske databaser for dansk","year":"2010","journal-title":"Nordisk Spraakteknologi Holding as (NST)"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/9781315154718"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916407"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2022.107951"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747120"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053266"},{"key":"ref73","first-page":"1","article-title":"Phase-aware speech enhancement with deep complex U-Net","author":"choi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref72","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc 18th Int Conf Med Image Comput Comput -Assist Interv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/10.0005089"},{"key":"ref68","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2561"},{"key":"ref67","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","article-title":"PNL 100 nonspeech sounds","author":"hu","year":"2010"},{"key":"ref25","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","author":"garofolo","year":"1993"},{"key":"ref69","article-title":"Exploring the best loss function for DNN-based low-latency speech enhancement with temporal convolutional networks","author":"koyama","year":"2020"},{"key":"ref20","article-title":"Deep neural network based supervised speech segregation generalizes to novel noises through large-scale training","author":"wang","year":"2015"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1121\/1.4820893"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2628641"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2765819"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-552"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1109\/TAU.1969.1162058","article-title":"IEEE recommended practice for speech quality measurements","volume":"17","author":"rothauser","year":"1969","journal-title":"IEEE Trans Audio Electroacoust"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1121\/1.1506692"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-431"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097075"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10262301.pdf?arnumber=10262301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:35:30Z","timestamp":1699904130000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10262301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3318965","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}