{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:58:41Z","timestamp":1776884321687,"version":"3.51.2"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Serbian Ministry of Education"},{"name":"Science and Technological Development","award":["TR 32032"],"award-info":[{"award-number":["TR 32032"]}]},{"name":"Science and Technological Development","award":["OI 178027"],"award-info":[{"award-number":["OI 178027"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/taslp.2017.2738559","type":"journal-article","created":{"date-parts":[[2017,11,23]],"date-time":"2017-11-23T19:08:05Z","timestamp":1511464085000},"page":"2313-2322","source":"Crossref","is-referenced-by-count":62,"title":["Whispered Speech Recognition Using Deep Denoising Autoencoder and Inverse Filtering"],"prefix":"10.1109","volume":"25","author":[{"given":"Dorde T.","family":"Grozdic","sequence":"first","affiliation":[]},{"given":"Slobodan T.","family":"Jovicic","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30441-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref32","article-title":"Signal processing using the Teager energy operator and other\n nonlinear operators","author":"kvedalen","year":"2003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/78.277799"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163453"},{"key":"ref37","first-page":"110","article-title":"Flexible speaker adaptation using maximum likelihood linear regression","author":"leggetter","year":"0","journal-title":"Proc ARPA Spoken Lang Technol Workshop"},{"key":"ref36","author":"young","year":"2002","journal-title":"The HTK Book (for HTK Version 3 2)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref34","first-page":"157","article-title":"Application of inverse filtering in enhancement of whisper recognition","author":"grozdi?","year":"0","journal-title":"Proc IEEE Neural Netw Appl Elect Eng"},{"key":"ref10","first-page":"3013","article-title":"Auditory teager energy cepstrum coefficients for robust speech recognition","author":"dimitriadis","year":"0","journal-title":"Proc EUSPICO"},{"key":"ref11","first-page":"31","article-title":"Using teager energy cepstrum and HMM distances","volume":"5","author":"heracleous","year":"2009","journal-title":"Int J Inform Commun Eng"},{"key":"ref12","first-page":"549","article-title":"Classification of speech under stress based on features derived from the nonlinear Teager energy operator","author":"zhou","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40585-3_74"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2066967"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854059"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639243"},{"key":"ref17","first-page":"1598","article-title":"A whispered mandarin corpus for speech\n technology applications","author":"lee","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11581-8_31"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.2702.251"},{"key":"ref4","article-title":"Computational differences between whispered and non-whispered\n speech","author":"lim","year":"2011"},{"key":"ref27","first-page":"2396","article-title":"Analysis and classification of speech mode: Whispered through shouted","author":"zhang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2012-157"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319457"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2012.6423522"},{"key":"ref8","first-page":"5","article-title":"Adaptation for soft\n whisper recognition using a throat microphone","author":"jou","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178927"},{"key":"ref2","article-title":"Enhancement and recognition of whispered speech","author":"morris","year":"2003"},{"key":"ref9","first-page":"1154","article-title":"Lipreading approach for isolated digits recognition under whisper and neutral speech","author":"tao","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2006.08.012"},{"key":"ref20","first-page":"2420","article-title":"Model\n and feature based compensation for whispered speech recognition","author":"ghaffarzadegan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2580944"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034770"},{"key":"ref24","first-page":"77","article-title":"Serbian emotional speech database: Design, processing and evaluation","author":"jovi?i?","year":"0","journal-title":"Proc 9th Conf Speech Comput"},{"key":"ref23","first-page":"728","article-title":"Application\n of neural networks in whispered speech recognition","author":"grozdi?","year":"0","journal-title":"20th Telecommunication Forum"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2091631"},{"key":"ref25","first-page":"739","article-title":"Formant feature differences between whispered and voiced sustained\n vowels","volume":"84","author":"jovicic","year":"1998","journal-title":"Acta Acust United with Acust"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8114348\/08114355.pdf?arnumber=8114355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:24:07Z","timestamp":1642004647000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8114355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":38,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2738559","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}