{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T05:59:25Z","timestamp":1768456765422,"version":"3.49.0"},"reference-count":80,"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":"am","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"}],"funder":[{"DOI":"10.13039\/100000005","name":"U.S. Department of Defense","doi-asserted-by":"publisher","award":["FA8702-15-D-0001"],"award-info":[{"award-number":["FA8702-15-D-0001"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]}],"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.2024.3389632","type":"journal-article","created":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T17:34:35Z","timestamp":1713461675000},"page":"2418-2431","source":"Crossref","is-referenced-by-count":5,"title":["A Multiscale Autoencoder (MSAE) Framework for End-to-End Neural Network Speech Enhancement"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8529-5378","authenticated-orcid":false,"given":"Bengt J.","family":"Borgstr\u00f6m","sequence":"first","affiliation":[{"name":"MIT Lincoln Laboratory, Artificial Intelligence Technology and Systems Group, Lexington, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7883-3658","authenticated-orcid":false,"given":"Michael S.","family":"Brandstein","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory, Artificial Intelligence Technology and Systems Group, Lexington, MA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045180"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1097\/aud.0b013e31820512bb"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288811"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/9781118392683"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288857"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2311329"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163394"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/97.1001645"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3043655"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462593"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1223"},{"key":"ref17","article-title":"Improved speech enhancement with the wave-u-net","author":"Macartney","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2290"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461737"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462622"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2913512"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2953810"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937186"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-021-00207-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054401"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052968"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2968738"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3079813"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3225649"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746169"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref42","article-title":"Real-time monaural speech enhancement with short-time discrete cosine transform","author":"Li","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/nn0402-292"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.1970.5213512"},{"key":"ref45","volume-title":"Spectral Audio Signal Processing","author":"Smith","year":"2011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-374370-1.x0001-8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.243"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-30"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2018.8645535"},{"key":"ref55","volume-title":"Discrete-Time Speech Signal Processing: Principles and Practice","author":"Quatieri","year":"2008"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828980"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201259"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1384"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1454"},{"key":"ref65","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1974.9484"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2877909"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref75","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3038"},{"key":"ref78","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014"},{"key":"ref79","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref80","article-title":"SCTK, the NIST scoring toolkit","author":"Fiscus","year":"2021"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/10304349\/10504992-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10504992.pdf?arnumber=10504992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:59:43Z","timestamp":1714762783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10504992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3389632","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}