{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:18:56Z","timestamp":1760710736398,"version":"3.37.3"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"The Institute of Statistical Mathematics, Tachikawa-shi, Tokyo, Japan"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3117080","type":"journal-article","created":{"date-parts":[[2021,10,2]],"date-time":"2021-10-02T01:53:38Z","timestamp":1633139618000},"page":"136831-136860","source":"Crossref","is-referenced-by-count":8,"title":["Machine Learning Mitigants for Speech Based Cyber Risk"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2797-4529","authenticated-orcid":false,"given":"Marta","family":"Campi","sequence":"first","affiliation":[]},{"given":"Gareth W.","family":"Peters","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1543-5440","authenticated-orcid":false,"given":"Nourddine","family":"Azzaoui","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3201-6106","authenticated-orcid":false,"given":"Tomoko","family":"Matsui","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-44"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref71","article-title":"ASVspoof 2015: The first automatic speaker verification spoofing and countermeasures challenge","author":"wu","year":"2015","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2698143"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660175"},{"key":"ref39","first-page":"23","article-title":"Text-independent speaker identification system using average pitch and formant analysis","volume":"3","author":"a","year":"2014","journal-title":"Int J Inf Theory"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.427150"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2015.00126"},{"key":"ref32","first-page":"2733","article-title":"Robust speaker recognition in non-stationary room environments based on empirical mode decomposition","author":"hasan","year":"2011","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1661"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cnsns.2019.104983"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39348-8"},{"article-title":"Nonparametric smoothing lecture notes","year":"2017","author":"bowman","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-8387-7_69"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WOSSPA.2011.5931414"},{"key":"ref62","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"Proc 9th Speech Synth Workshop (ISCA)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164910"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900396"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221460"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01132-1_43"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1978.1170401"},{"key":"ref67","first-page":"310","article-title":"A comparative study of filter bank spacing for speech recognition","volume":"41","author":"shannon","year":"2003","journal-title":"Proc Microelectronic Eng Res Conf"},{"key":"ref68","article-title":"Evaluating gammatone frequency cepstral coefficients with neural networks for emotion recognition from speech","author":"liu","year":"2018","journal-title":"arXiv 1806 09010"},{"key":"ref69","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICEE49691.2020.9249786"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISRITI48646.2019.9034603"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3844\/jcssp.2016.56.61"},{"key":"ref22","first-page":"2211","article-title":"Multiple kernel learning algorithms","volume":"12","author":"g\u00f6nen","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3090109"},{"journal-title":"Spoken Language Processing A Guide to Theory Algorithm and System Development","year":"2001","author":"huang","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3025941"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.884031"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960641"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.17762\/ijritcc2321-8169.150474"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICEEOT.2016.7755666"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2019.21"},{"journal-title":"A comparison of features for synthetic speech detection","year":"2015","author":"sahidullah","key":"ref56"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5120\/17740-8271"},{"key":"ref53","first-page":"121","article-title":"RASTA-PLP speech analysis","volume":"1","author":"hermansky","year":"1991","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.08.007"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2671435"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2682788"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISCCSP.2004.1296465"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3084299"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(01)00235-7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960643"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICICT.2017.8320160"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-81-322-3592-7_9"},{"key":"ref18","first-page":"11","article-title":"Improved text-independent speaker identification using fused MFCC & IMFCC feature sets based on Gaussian filter","volume":"5","author":"chakroborty","year":"2009","journal-title":"Int J Signal Process"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659746"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1998.0193"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/02664763.2016.1267122"},{"key":"ref6","first-page":"2074","article-title":"Empirical mode decomposition for noise-robust automatic speech recognition","author":"wu","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.12.004"},{"key":"ref8","first-page":"2347","article-title":"A new algorithm for instantaneous F0 speech extraction based on ensemble empirical mode decomposition","author":"schlotthauer","year":"2009","journal-title":"Proc 17th Eur Signal Process Conf"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518785"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1136"},{"key":"ref9","first-page":"632","article-title":"Front-end for antispoofing countermeasures in speaker verification: Scattering spectral decomposition","volume":"11","author":"sriskandaraja","year":"2016","journal-title":"IEEE J Sel Topics Signal Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ITWNIT.2009.5158542"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1051\/ps:2005018"},{"key":"ref48","first-page":"701","article-title":"Recent research in automatic speaker recognition","author":"rosenberg","year":"1992","journal-title":"Advances in Speech Signal Processing"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1969.1162058"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"cortes","year":"1995","journal-title":"Mach Learn"},{"key":"ref41","first-page":"286","article-title":"Mel frequency cepstral coefficients: An evaluation of robustness of MP3 encoded music","author":"sigurdsson","year":"2006","journal-title":"Proc 7th Int Conf Music Inf Retr (ISMIR)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/RIVF.2008.4586335"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09555610.pdf?arnumber=9555610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:49Z","timestamp":1639770949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9555610\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3117080","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}