{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:22:14Z","timestamp":1760955734019,"version":"3.37.3"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2017,11,1]],"date-time":"2017-11-01T00:00:00Z","timestamp":1509494400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005416","name":"Research Council of Norway","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["H2020"],"award-info":[{"award-number":["H2020"]}],"id":[{"id":"10.13039\/501100000780","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":[[2017,11]]},"DOI":"10.1109\/taslp.2017.2743340","type":"journal-article","created":{"date-parts":[[2017,8,23]],"date-time":"2017-08-23T18:13:23Z","timestamp":1503512003000},"page":"2098-2111","source":"Crossref","is-referenced-by-count":36,"title":["Long-Term Spectral Statistics for Voice Presentation Attack Detection"],"prefix":"10.1109","volume":"25","author":[{"given":"Hannah","family":"Muckenhirn","sequence":"first","affiliation":[]},{"given":"Pavel","family":"Korshunov","sequence":"additional","affiliation":[]},{"given":"Mathew","family":"Magimai-Doss","sequence":"additional","affiliation":[]},{"given":"Sebastien","family":"Marcel","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/S0892-1997(01)00034-0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0892-1997(96)80019-1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916034"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/S0095-4470(19)30692-8","article-title":"The long-time-average spectrum as a tool in voice research","volume":"14","author":"l\u00f6fqvist","year":"1986","journal-title":"J Phonetics"},{"key":"ref31","first-page":"559","article-title":"On the use of long-term average spectrum in automatic speaker recognition","author":"kinnunen","year":"0","journal-title":"Proc Int Symp Chinese Spoken Language Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1590\/S0104-56872006000100013"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"77","DOI":"10.3233\/NRE-141102","article-title":"Long-time average spectrum in individuals with parkinson disease","volume":"35","author":"smith","year":"2014","journal-title":"Neurorehabilitation"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2004.02.005"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916407"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2684705"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-2037-8_2"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-844"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2647199"},{"key":"ref64","first-page":"1766","article-title":"Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks","author":"palaz","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref27","first-page":"2067","article-title":"Robust deep feature for spoofing detection - the SJTU system for ASVspoof 2015 challenge","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"article-title":"End-to-end acoustic modeling using convolutional neural networks for automatic speech recognition","year":"2016","author":"palaz","key":"ref65"},{"key":"ref29","first-page":"2097","article-title":"Spoofing detection with DNN and one-class SVM for the ASVspoof 2015 challenge","author":"villalba","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2015.7358783"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1147\/sj.403.0614"},{"key":"ref20","first-page":"2062","article-title":"Combining evidences from mel cepstral, cochlear filter cepstral and instantaneous frequency features for detection of natural vs. spoofed speech","author":"patel","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","first-page":"2092","article-title":"Relative phase information for detecting human speech and spoofed speech","author":"wang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref21","first-page":"2072","article-title":"Development of CRIM system for the automatic speaker verification spoofing and countermeasures challenge 2015","author":"alam","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref24","first-page":"370","article-title":"Synthetic speech discrimination using pitch pattern statistics derived from image analysis","author":"leon","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref23","first-page":"2082","article-title":"Simultaneous utilization of spectral magnitude and phase information to extract supervectors for speaker verification anti-spoofing","author":"liu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref26","first-page":"239","article-title":"Voice liveness detection algorithms based on pop noise caused by human breath for automatic speaker verification","author":"shiota","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/ietfec\/E88-A.1.280"},{"article-title":"ICSI quicknet software package","year":"2004","author":"johnson","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2016.7791200"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-41"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472724"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164788"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.01.005"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596192"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1326"},{"key":"ref11","first-page":"2052","article-title":"Spoofing speech detection using high dimensional magnitude and phase features: The NTU approach for ASVspoof 2015 challenge","author":"xiao","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref40","first-page":"206","article-title":"Long-term average spectrum study on speaking voice quality in male actors","author":"leino","year":"0","journal-title":"Proc Stockholm Music Acoust Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472051"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2671435"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2201472"},{"key":"ref15","first-page":"1700","article-title":"Detecting converted speech and natural speech for anti-spoofing attack in speaker recognition","author":"wu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639067"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2013.6712706"},{"key":"ref18","first-page":"940","article-title":"A new speaker verification spoofing countermeasure based on local binary patterns","author":"alegre","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.12.003"},{"year":"2016","key":"ref4","article-title":"DIS 30107-1, information technology—Biometrics presentation attack detection"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref6","first-page":"2037","article-title":"ASVspoof 2015: The first automatic speaker verification spoofing and countermeasures challenge","author":"wu","year":"0","journal-title":"Proc INTERSPEECH"},{"article-title":"Can a professional imitator fool a GMM-based speaker verification system","year":"2005","author":"mari\u00e9thoz","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396517"},{"key":"ref7","first-page":"2087","article-title":"A comparison of features for synthetic speech detection","author":"sahidullah","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref49","first-page":"517","author":"huang","year":"2001","journal-title":"Spoken Language Processing A Guide to Theory Algorithm and System Development"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/BIOSIG.2016.7736933"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1981.1163530"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2004.1328092"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-21"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2174223"},{"key":"ref42","first-page":"113","article-title":"Towards an improved modeling of the glottal source in statistical parametric speech synthesis","author":"cabral","year":"0","journal-title":"Proc 6th ISCA Speech Synth Workshop"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012213564-4\/50007-X"},{"key":"ref44","first-page":"209","article-title":"The quefrency analysis of time series for echoes: Cepstrum, pseudo-autocovariance, cross-cepstrum and saphe cracking","author":"bogert","year":"0","journal-title":"Proc Symp Time Series Anal"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853598"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8047434\/08015145.pdf?arnumber=8015145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:03:18Z","timestamp":1642003398000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8015145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":65,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2743340","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2017,11]]}}}