{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T08:05:20Z","timestamp":1725609920188},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1109\/taslp.2021.3082702","type":"journal-article","created":{"date-parts":[[2021,5,21]],"date-time":"2021-05-21T15:46:29Z","timestamp":1621611989000},"page":"1937-1949","source":"Crossref","is-referenced-by-count":14,"title":["SNR-Based Features and Diverse Training Data for Robust DNN-Based Speech Enhancement"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-7458-2320","authenticated-orcid":false,"given":"Robert","family":"Rehr","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8678-4699","authenticated-orcid":false,"given":"Timo","family":"Gerkmann","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","first-page":"1","article-title":"Data-driven speech enhancement","author":"fingscheidt","year":"0","journal-title":"Proc ITG Conf Speech Commun"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.06.012"},{"key":"ref71","first-page":"1","article-title":"A general optimization procedure for spectral speech enhancement methods","author":"erkelens","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366903"},{"key":"ref76","article-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus LDC93S1","author":"garofolo","year":"1993"},{"key":"ref77","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.920062"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref75","first-page":"1508","article-title":"Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement","author":"xu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2016.7602888"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref79","article-title":"Perceptual objective listening quality prediction","year":"2018"},{"key":"ref33","first-page":"26","article-title":"Noise-presence-probability-based noise PSD estimation by using DNNs","author":"chinaev","year":"0","journal-title":"ITG Conf Speech Commun"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.02.001"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045799"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90009-T"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032183"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-437"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682991"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1979.1170788"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082266"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719246"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1672"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2025795"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"ref65","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462155"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221459"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2817798"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885256"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2014.6843245"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2014.0032"},{"key":"ref24","first-page":"22","article-title":"Recurrent neural networks for noise reduction in robust ASR","author":"maas","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref23","first-page":"6206","article-title":"Non-negative source-filter dynamical system for speech enhancement","author":"?im?ekli","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2618007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854478"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895570"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2628641"},{"key":"ref59","first-page":"126","article-title":"Robust DNN-based speech enhancement with limited training data","author":"rehr","year":"0","journal-title":"Proc ITG Conf Speech Commun"},{"key":"ref58","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van den maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref55","first-page":"2067","article-title":"A tandem algorithm for pitch estimation and voiced speech segregation","volume":"18","author":"hu","year":"0","journal-title":"IEEE Trans Audio Speech and Language Process"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3016487"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref10","first-page":"1319","article-title":"Log-spectral magnitude MMSE estimators under super-Gaussian densities","author":"hendriks","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/97.988717"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/89.928915"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518755"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2180896"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.854113"},{"key":"ref82","first-page":"3221","article-title":"Accelerating t-SNE using tree-based algorithms","volume":"15","author":"van den maaten","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2172943"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2636445"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/89.709670"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.803420"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1155\/ASP.2005.1110"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2008.4685528"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/78.127947"},{"key":"ref6","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","volume":"2013","author":"lu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270369"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518540"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-88"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2001108"},{"key":"ref46","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2015.7394335"},{"key":"ref48","first-page":"2670","article-title":"Dynamic noise aware training for speech enhancement based on deep neural networks","author":"xu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6953357"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/1.4986931"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09439068.pdf?arnumber=9439068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:01Z","timestamp":1652194441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9439068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3082702","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}