{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:59:28Z","timestamp":1776884368260,"version":"3.51.2"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2016,10,1]],"date-time":"2016-10-01T00:00:00Z","timestamp":1475280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","award":["FA8750-15-1-0205"],"award-info":[{"award-number":["FA8750-15-1-0205"]}],"id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University of Texas at Dallas from the Distinguished University Chair in Telecommunications Engineering"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/taslp.2016.2580944","type":"journal-article","created":{"date-parts":[[2016,6,14]],"date-time":"2016-06-14T18:52:22Z","timestamp":1465930342000},"page":"1705-1720","source":"Crossref","is-referenced-by-count":19,"title":["Generative Modeling of Pseudo-Whisper for Robust Whispered Speech Recognition"],"prefix":"10.1109","volume":"24","author":[{"given":"Shabnam","family":"Ghaffarzadegan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hynek","family":"Boril","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John H. L.","family":"Hansen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(95)00007-B"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/89.326618"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref32","article-title":"UTDrive: Emotion and cognitive load classification for in-vehicle scenarios","author":"bo?il","year":"2011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.02.002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.07.005"},{"key":"ref37","first-page":"1125","article-title":"Lombard effect compensation for robust automatic speech recognition in noise","author":"hansen","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169551"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1121\/1.402044"},{"key":"ref34","first-page":"464","article-title":"WaveSurfer - an open source speech tool","volume":"4","author":"sjolander","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607987"},{"key":"ref62","article-title":"Praat: Doing phonetics by computer (version 4.4.33)","author":"boersma","year":"2006"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E92.D.2244"},{"key":"ref27","article-title":"Communication in noisy environments: From adaptation to vocal straining","author":"garnier","year":"2007"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.3478775"},{"key":"ref2","first-page":"2420","article-title":"Model and feature based compensation for whispered speech recognition","author":"ghaffarzadegan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854059"},{"key":"ref20","first-page":"180","article-title":"Constrained lexicon speaker dependent recognition of whispered speech","author":"galic","year":"0","journal-title":"Proc Int Symp Ind Electron"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.07.002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/NEUREL.2014.7011492"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90010-7"},{"key":"ref23","first-page":"860","article-title":"Advancement in whisper-island detection with normally phonated audio streams","author":"zhang","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref26","article-title":"Robust speech recognition: Analysis and equalization of Lombard effect in Czech corpora","author":"bo?il","year":"2008"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(96)00050-7"},{"key":"ref50","article-title":"Speech recognition in noisy environments","author":"moreno","year":"1996"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853900"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1121\/1.1914702"},{"key":"ref58","article-title":"RASTA\/PLP\/MFCC feature calculation and inversion","year":"2013"},{"key":"ref57","article-title":"CMUSphinx—Open source toolkit for speech recognition","author":"university","year":"2013"},{"key":"ref56","first-page":"153","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"2007","journal-title":"Neural Information Processing"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref54","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref52","first-page":"3512","article-title":"Reverberant speech recognition based on denoising autoencoder","author":"ishii","year":"0","journal-title":"Proc Int Speech Commun Assoc"},{"key":"ref10","first-page":"429","article-title":"Acoustic analysis and recognition of whispered speech","author":"ito","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recog and Understanding"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/89.799692"},{"key":"ref11","first-page":"131","article-title":"Comparative study of male and female whispered and phonated versions of the long vowels of Swedish","volume":"37","author":"eklund","year":"1996","journal-title":"Phonetica"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.005"},{"key":"ref13","article-title":"Computational differences between whispered and non-whispered speech","author":"lim","year":"2011"},{"key":"ref14","first-page":"133","article-title":"Acoustic nature of the whisper","author":"matsuda","year":"0","journal-title":"Proc 6th Eur Conf Speech Commun Technol"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2010.12.002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2012-157"},{"key":"ref17","first-page":"1009","article-title":"Whispery speech recognition using adapted articulatory features","volume":"1","author":"jou","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2012.6423522"},{"key":"ref19","first-page":"1154","article-title":"Lipreading approach for isolated digits recognition under whisper and neutral speech","author":"tao","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S1350-4533(02)00060-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178927"},{"key":"ref6","first-page":"1598","article-title":"A whispered Mandarin corpus for speech technology applications","author":"lee","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.4868359"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495059"},{"key":"ref49","first-page":"869","article-title":"HMM adaptation using vector Taylor series for noisy speech recognition","author":"acero","year":"0","journal-title":"Proc Int Speech Commun Assoc"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2010.5757831"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2091631"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-119","article-title":"Speaker normalization through formant-based warping of the frequency scale","author":"gouva","year":"1997"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541103"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543225"},{"key":"ref47","first-page":"3937","article-title":"Unsupervised equalization of Lombard effect for speech recognition in noisy adverse environment","author":"bo?il","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541105"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/89.848224"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034770"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596120"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7524661\/07491308.pdf?arnumber=7491308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T16:47:34Z","timestamp":1718642854000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7491308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":62,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2580944","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,10]]}}}