{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T13:54:03Z","timestamp":1791986043937,"version":"4.4.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2016,7,1]],"date-time":"2016-07-01T00:00:00Z","timestamp":1467331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-0420866"],"award-info":[{"award-number":["IIS-0420866"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-0916918"],"award-info":[{"award-number":["IIS-0916918"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency (DARPA)","doi-asserted-by":"publisher","award":["D10PC20024"],"award-info":[{"award-number":["D10PC20024"]}],"id":[{"id":"10.13039\/100000185","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":[[2016,7]]},"DOI":"10.1109\/taslp.2016.2545928","type":"journal-article","created":{"date-parts":[[2016,3,23]],"date-time":"2016-03-23T18:18:20Z","timestamp":1458757100000},"page":"1315-1329","source":"Crossref","is-referenced-by-count":223,"title":["Power-Normalized Cepstral Coefficients (PNCC) for Robust Speech Recognition"],"prefix":"10.1109","volume":"24","author":[{"given":"Chanwoo","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0557-7282","authenticated-orcid":false,"given":"Richard M.","family":"Stern","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","author":"ellis","year":"2006","journal-title":"PLP and RASTA (and MFCC and Inversion) in Matlab Using Melfcc m and Invmelfcc m"},{"key":"ref72","year":"0","journal-title":"CMU Sphinx Open Source Toolkit for Speech Recognition Downloads"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref70","article-title":"Room impulse response generator","author":"mcgovern","year":"2013"},{"key":"ref39","first-page":"335","article-title":"A revision of Zwicker’s loudness model","volume":"82","author":"moore","year":"1996","journal-title":"ACUSTICA–acta acustica"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-041847-6.50054-X"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2179294"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2011.5940729"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25775-9_20"},{"key":"ref30","article-title":"Comparação dos atributos MFCC, SSCH e PNCC para reconhecimento robusto de voz contínua","author":"siqueira","year":"0","journal-title":"Proceedings of the XXI Simpósio Brasileiro de Telecomunicações"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/MSP.2012.2207989","article-title":"Hearing is believing: Biologically-inspired feature extraction for robust automatic speech recognition","volume":"29","author":"stern","year":"2012","journal-title":"Signal Process Mag"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/9781118392683.ch8"},{"key":"ref34","first-page":"4697","article-title":"Histogram-based subband power warping and spectral averaging for robust speech recognition under matched and multistyle training","author":"harvilla","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373230"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/S0095-4470(19)30466-8","article-title":"A joint synchrony\/mean-rate model of auditory speech processing","volume":"16","author":"seneff","year":"1988","journal-title":"J Phonetics"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1511828"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/89.294356"},{"key":"ref28","first-page":"1968","article-title":"A comparison of auditory features for robust speech recognition","author":"kelly","year":"0","journal-title":"Proc EUSIPCO"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1121\/1.1387155"},{"key":"ref27","first-page":"591","article-title":"Robust parameters for speech recognition based on subband spectral centroid histograms","author":"gajic","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1121\/1.427950"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1121\/1.1336503"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.1082"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1121\/1.1336503"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1037\/h0046162"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288820"},{"key":"ref2","author":"jelinek","year":"1998","journal-title":"Statistical Methods for Speech Recognition (Language Speech and Communication)"},{"key":"ref1","author":"rabiner","year":"1993","journal-title":"Fundamentals of speech recognition"},{"key":"ref20","first-page":"898","article-title":"Multi-stream spectro-temporal features for robust speech recognition","author":"zhao","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495570"},{"key":"ref21","first-page":"28","article-title":"Feature extraction for robust speech recognition using a power-law nonlinearity and power-bias subtraction","author":"kim","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/89.736331"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.02.002"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.07.006"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1121\/1.428100"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479387"},{"key":"ref59","first-page":"2495","article-title":"Signal separation for robust speech recognition based on phase difference information obtained in the frequency domain","author":"kim","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1121\/1.387576"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659979"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947497"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.1997.625622"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2010884"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518720"},{"key":"ref52","first-page":"2058","article-title":"Nonlinear enhancement of onset for robust speech recognition","author":"kim","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325955"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596069"},{"key":"ref40","article-title":"Auditory toolbox version 2","author":"slaney","year":"1998"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495668"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.006"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.07.002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858055"},{"key":"ref18","first-page":"2573","article-title":"Localized spectro-temporal features for automatic speech recognition","author":"kleinschmidt","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref19","first-page":"4165","article-title":"Hierarchical and parallel processing of modulation spectrum for ASR applications","author":"hermansky","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543225"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115971"},{"key":"ref6","first-page":"33","article-title":"Compensation for environmental degradation in automatic speech recognition","author":"stern","year":"0","journal-title":"Proc ESCA Tut Res Workshop Robust Speech Recognit Unknown Commun Channels"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660135"},{"key":"ref8","article-title":"Speech Processing, Transmission and Quality Aspects (STQ); Distributed Speech Recognition; Advanced Front-end Feature Extraction Algorithm; Compression Algorithms, European Telecommunications Standards Institute ES 202 050, Rev. 1.1.5","year":"2007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1201\/9781420041262.ch9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1121\/1.414959"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2001.1034579"},{"key":"ref46","first-page":"109","article-title":"Improved feature processing for deep neural networks","author":"rath","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1109\/LSP.2008.2002708","article-title":"Recognition of reverberant speech using frequency domain linear prediction","volume":"15","author":"ganapathy","year":"2008","journal-title":"IEEE Signal Process Lett"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00032-6"},{"key":"ref47","article-title":"Signal processing for robust speech recognition motivated by auditory processing","author":"kim","year":"2010"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373233"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2001.1034598"},{"key":"ref44","first-page":"949","article-title":"LP-TRAP: Linear predictive temporal patterns","author":"athineos","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758119"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/iel7\/6570655\/7466869\/07439789.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7466869\/07439789.pdf?arnumber=7439789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T02:27:57Z","timestamp":1655346477000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7439789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7]]},"references-count":73,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2545928","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7]]}}}