{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:05:21Z","timestamp":1775228721298,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T00:00:00Z","timestamp":1533081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/I031022\/1 (NST)"],"award-info":[{"award-number":["EP\/I031022\/1 (NST)"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/J002526\/1 (CAF)"],"award-info":[{"award-number":["EP\/J002526\/1 (CAF)"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CREST from the Japan Science and Technology Agency"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/taslp.2018.2828980","type":"journal-article","created":{"date-parts":[[2018,4,20]],"date-time":"2018-04-20T18:08:47Z","timestamp":1524247727000},"page":"1420-1433","source":"Crossref","is-referenced-by-count":34,"title":["Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3486-8620","authenticated-orcid":false,"given":"Cassia","family":"Valentini-Botinhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3955","authenticated-orcid":false,"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","year":"2010","journal-title":"Speech Signal Processing Toolkit SPTK 3 4"},{"key":"ref38","first-page":"1","article-title":"Aperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system STRAIGHT","author":"kawahara","year":"2001","journal-title":"Proc MAVEBA"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811544"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1684(01)00128-1"},{"key":"ref31","article-title":"Room Impulse Response Generator","author":"habets","year":"2010"},{"key":"ref30","first-page":"1","article-title":"Evaluation of speech dereverberation algorithms using the MARDY database","author":"wen","year":"2006","journal-title":"Proc Int Workshop Acoust Echo Noise Control"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref36","first-page":"1","article-title":"Fast signal reconstruction from magnitude STFT spectrogram based on spectrogram consistency","volume":"10","author":"roux","year":"0","journal-title":"Proc Int Conf Dig Audio Effects"},{"key":"ref35","first-page":"547","article-title":"Introducing CURRENNT: The munich open-source CUDA RecurREnt neural network toolkit","volume":"16","author":"weninger","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref34","article-title":"Postfish—Xiph SVN repository","year":"0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6954309"},{"key":"ref27","year":"1993","journal-title":"Recommendation P 56 Objective measurement of active speech level"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336912"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2278492"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1250\/ast.33.1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2008042"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2416653"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1201\/9781420015836","author":"loizou","year":"2007","journal-title":"Speech Enhancement Theory and Practice"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1121\/1.4806631"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref50","first-page":"225","article-title":"IEEE recommended practice for speech quality measurement","volume":"ae 17","year":"1969","journal-title":"IEEE Trans Audio Electroacoustics"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1647"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.12.003"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-733"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1672"},{"key":"ref52","article-title":"A wavenet for speech denoising","volume":"abs 1706 7162","author":"rethage","year":"2017","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref40","first-page":"495","article-title":"A robust algorithm for pitch tracking","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref12","first-page":"1","article-title":"Joint dereverberation and noise reduction using beamforming and a single-channel speech enhancement scheme","author":"cauchi","year":"2014","journal-title":"Proc REVERB Challenge Workshop"},{"key":"ref13","first-page":"359","article-title":"A new method based on spectral subtraction for speech dereverberation","volume":"87","author":"lebart","year":"2001","journal-title":"Acta Acust"},{"key":"ref14","first-page":"1","article-title":"The NTU-ADSC systems for reverberation challenge 2014","author":"xiao","year":"2014","journal-title":"Proc REVERB Challenge Workshop"},{"key":"ref15","first-page":"1","article-title":"The MERL\/MELCO\/TUM system for the REVERB challenge using deep recurrent neural network feature enhancement","author":"weninger","year":"2014","journal-title":"Proc REVERB Challenge Workshop"},{"key":"ref16","first-page":"758","article-title":"Speech denoising and dereverberation using probabilistic models","volume":"13","author":"attias","year":"2001","journal-title":"Adv Neural Inform Process Syst"},{"key":"ref17","first-page":"854","author":"kinoshita","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2002071"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.12.006"},{"key":"ref3","first-page":"2331","article-title":"Tundra: A multilingual corpus of found data for TTS research created with light supervision","author":"stan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23","author":"xu","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178800"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032183"},{"key":"ref7","first-page":"1760","article-title":"Text-informed speech enhancement with deep neural networks","author":"kinoshita","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref49","year":"2003","journal-title":"Method for the Subjective Assessment of Intermediate Quality Level of Coding Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref46","first-page":"1","article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","author":"patton","year":"0","journal-title":"Proc NIPS 2016 End-to-end Learning Speech Audio Process Workshop"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref42","first-page":"139","article-title":"Noise robustness in HMM-TTS speaker adaptation","author":"yanagisawa","year":"2013","journal-title":"Proc IEEE Workshop Speech Synthesis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"995","DOI":"10.21437\/Interspeech.2012-295","article-title":"Analysis of speaker clustering strategies for HMM-based speech synthesis","author":"dall","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2016394"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8356719\/08343873.pdf?arnumber=8343873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,20]],"date-time":"2022-08-20T14:56:42Z","timestamp":1661007402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8343873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":58,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2828980","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8]]}}}