{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T19:40:08Z","timestamp":1751830808541,"version":"3.41.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/taslp.2018.2867947","type":"journal-article","created":{"date-parts":[[2018,8,31]],"date-time":"2018-08-31T18:51:03Z","timestamp":1535741463000},"page":"2460-2474","source":"Crossref","is-referenced-by-count":14,"title":["DNN-Supported Speech Enhancement With Cepstral Estimation of Both Excitation and Envelope"],"prefix":"10.1109","volume":"26","author":[{"given":"Samy","family":"Elshamy","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9131-3309","authenticated-orcid":false,"given":"Nilesh","family":"Madhu","sequence":"additional","affiliation":[]},{"given":"Wouter","family":"Tirry","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8895-5041","authenticated-orcid":false,"given":"Tim","family":"Fingscheidt","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"Proc Conf Artif Intell Statist"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1002\/0471721182","author":"mclachlan","year":"2000","journal-title":"Finite Mixture Models"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.1910339"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref31","first-page":"4033","article-title":"MMSE speech enhancement under speech presence uncertainty assuming (generalized) gamma priors throughout","author":"fodor","year":"2012","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1155\/ASP.2005.1110"},{"journal-title":"Fundamentals of speech recognition","year":"1993","author":"rabiner","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1980.1094577"},{"journal-title":"Practical Approaches to Speech Coding","year":"1987","author":"papamichalis","key":"ref35"},{"key":"ref34","first-page":"1081","article-title":"Overcoming the statistical independence assumption w.r.t. frequency in speech enhancement","author":"fingscheidt","year":"2005","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811544"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/89.928915"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2180896"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495680"},{"key":"ref20","first-page":"4390","article-title":"A deep neural network for time-domain signal reconstruction","author":"wang","year":"2015","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"2870","DOI":"10.21437\/Interspeech.2016-437","article-title":"Causal speech enhancement combining data-driven learning and suppression rule estimation","author":"mirsamadi","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170027"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2016.7602894"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761236"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.920062"},{"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","year":"2001","key":"ref51"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"journal-title":"Narrow-Band Hands-Free Communication in Motor Vehicles","year":"2015","key":"ref53"},{"journal-title":"Mapping Function for Transforming P 862 Raw Result Scores to MOS-LQO","year":"2003","key":"ref52"},{"key":"ref10","first-page":"51","article-title":"A combination of pre-trained approaches and generic methods for an improved speech enhancement","author":"rehr","year":"2016","journal-title":"ITG Conf Speech Commun"},{"key":"ref11","first-page":"5064","article-title":"Speech enhancement based on log spectral envelope model and harmonicity-derived spectral mask, and its coupling with feature compensation","author":"yoshioka","year":"2011","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"journal-title":"Pattern Classification","year":"2000","author":"duda","key":"ref40"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.21437\/Eurospeech.2003-243","article-title":"Speech enhancement using a-priori information","author":"srinivasan","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.854113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881696"},{"key":"ref15","article-title":"Noise codebook adaptation for codebook-based noise reduction","author":"rosenkranz","year":"2010","journal-title":"Proceedings of the Intl Workshop on Acoustic Echo and Noise Control"},{"key":"ref16","first-page":"6206","article-title":"Non-negative source-filter dynamical system for speech enhancement","author":"?im?ekli","year":"2014","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref17","first-page":"495","article-title":"A robust algorithm for pitch tracking (RAPT)","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/78.127947"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885256"},{"key":"ref4","first-page":"105","article-title":"Improved MMSE-based noise psd tracking using temporal cepstrum smoothing","author":"gerkmann","year":"2012","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2007.906208"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2025795"},{"key":"ref5","first-page":"4897","article-title":"A novel a priori SNR estimation approach based on selective cepstro-temporal smoothing","author":"breithaupt","year":"2008","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2702385"},{"key":"ref7","first-page":"106","article-title":"Two-stage speech enhancement with manipulation of the cepstral excitation","author":"elshamy","year":"2017","journal-title":"Proc Joint Workshop Hands-Free Speech Commun Microphone Arrays"},{"key":"ref49","first-page":"36","article-title":"On the optimization of speech enhancement systems using instrumental measures","author":"gustafsson","year":"1996","journal-title":"Workshop on Quality Assessment in Speech Audio and Image Communication"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.02.006"},{"journal-title":"Super Wideband Stereo Speech Database","year":"0","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.IR.4930"},{"key":"ref48","first-page":"1","article-title":"Torch7: A MATLAB-like environment for machine learning","author":"collobert","year":"2011","journal-title":"NIPS Workshop BigLearn"},{"journal-title":"Objective Measurement of Active Speech Level","year":"2011","key":"ref47"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"year":"2008","key":"ref44"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"3110","DOI":"10.21437\/Interspeech.2010-774","article-title":"The QUT-NOISE-TIMIT corpus for the evaluation of voice activity detection algorithms","author":"dean","year":"2010","journal-title":"Proc INTERSPEECH"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8440863\/08452964.pdf?arnumber=8452964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T19:04:40Z","timestamp":1751828680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8452964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":54,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2867947","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2018,12]]}}}