{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T10:29:45Z","timestamp":1779013785498,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Audio-PSS"},{"name":"THERESIAH"},{"DOI":"10.13039\/501100002347","name":"Bundesministerium für Bildung und Forschung","doi-asserted-by":"publisher","award":["02K16C201"],"award-info":[{"award-number":["02K16C201"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium für Bildung und Forschung","doi-asserted-by":"publisher","award":["13GW0209B"],"award-info":[{"award-number":["13GW0209B"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EU Seventh Framework Programme project DREAMS","award":["ITN-GA-2012-316969"],"award-info":[{"award-number":["ITN-GA-2012-316969"]}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["390895286\u2013EXC 2177\/1"],"award-info":[{"award-number":["390895286\u2013EXC 2177\/1"]}],"id":[{"id":"10.13039\/501100001659","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":[[2019,7]]},"DOI":"10.1109\/taslp.2019.2912123","type":"journal-article","created":{"date-parts":[[2019,5,8]],"date-time":"2019-05-08T00:48:44Z","timestamp":1557276524000},"page":"1151-1163","source":"Crossref","is-referenced-by-count":38,"title":["Non-Intrusive Speech Quality Prediction Using Modulation Energies and LSTM-Network"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0338-492X","authenticated-orcid":false,"given":"Benjamin","family":"Cauchi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7360-4249","authenticated-orcid":false,"given":"Kai","family":"Siedenburg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3934-3943","authenticated-orcid":false,"given":"Joao F.","family":"Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5739-2514","authenticated-orcid":false,"given":"Tiago H.","family":"Falk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3392-2381","authenticated-orcid":false,"given":"Simon","family":"Doclo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Goetze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"4037","article-title":"Parameterized MMSE spectral magnitude estimation for the enhancement of noisy speech","author":"breithaupt","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref38","year":"1993","journal-title":"Objective Measurement of Active Speech Level"},{"key":"ref33","first-page":"1","article-title":"Blind room acoustics characterization using recurrent neural networks and modulation spectrum dynamics","author":"santos","year":"0","journal-title":"Proc AES 60th Int Conf"},{"key":"ref32","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336912"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479278"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2640939"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-015-0242-x"},{"key":"ref28","first-page":"180","article-title":"Predicting the quality of processed speech by combining modulation-based features and model trees","author":"cauchi","year":"0","journal-title":"ITG Conf Speech Commun"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.03.005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007421302149"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-84996-056-4","author":"naylor","year":"2010","journal-title":"Speech Dereverberation"},{"key":"ref1","author":"benesty","year":"2008","journal-title":"Microphone Array Signal Processing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883177"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2009.2024697"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/bltj.20228"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2363788"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6953337"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-155"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6954293"},{"key":"ref50","year":"1980","journal-title":"General performance objectives applicable to all modern international circuits and national extension circuits"},{"key":"ref51","first-page":"114","article-title":"Objective quality and intelligibility prediction for users of assistive listening devices","volume":"32","author":"falk","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref56","year":"2009","journal-title":"Statistical Evaluation Procedure for POLQA"},{"key":"ref55","author":"sprinthall","year":"2013","journal-title":"Basic Statistical Analysis"},{"key":"ref54","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref52","article-title":"Keras","author":"chollet","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916407"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1121\/1.384464"},{"key":"ref40","author":"gradshteyn","year":"1994","journal-title":"Table of Integrals Series and Products"},{"key":"ref12","year":"1997","journal-title":"Method for the calculation of the speech intelligibility index"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2281574"},{"key":"ref15","year":"2001","journal-title":"Perceptual Evaluation of Speech Quality (PESQ) An Objective Method for End-to-End Speech Quality Assessment of Narrowband Telephone Networks and Speech Codecs"},{"key":"ref16","year":"2011","journal-title":"Perceptual Objective Listening Quality Assessment An Advanced Objective Perceptual Method for End-to-End Listening Speech Quality Evaluation of Fixed Mobile and IP-Based Networks and Speech Codecs Covering Narrowband Wideband and Super-Wideband Signals"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883259"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.10.004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2366780"},{"key":"ref6","year":"2003","journal-title":"Subjective Test Methodology for Evaluating Speech Communication Systems That Include Noise Suppression Algorithms"},{"key":"ref5","first-page":"1","article-title":"A summary of the REVERB challenge: State-of-the-art and remaining challenges in reverberant speech processing research","volume":"2016","author":"kinoshita","year":"2015","journal-title":"EURASIP J Adv Signal Process"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/02699200400024863"},{"key":"ref7","year":"2003","journal-title":"Method for the Subjective Assessment of Intermediate Quality Levels of Coding Systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1987.1165054"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.4979580"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2180896"},{"key":"ref45","first-page":"4897","article-title":"A novel a priori SNR estimation approach based on selective cepstro-temporal smoothing","author":"breithaupt","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00042-X"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2641904"},{"key":"ref41","article-title":"Summary of the reverb challenge","author":"kinoshita","year":"2015"},{"key":"ref44","first-page":"359","article-title":"A new method based on spectral subtraction for speech de-reverberation","volume":"87","author":"lebart","year":"2001","journal-title":"Acta Acoustica"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/89.928915"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8708698\/08693793.pdf?arnumber=8693793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:45:01Z","timestamp":1657745101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8693793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":56,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2912123","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7]]}}}