{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:34:34Z","timestamp":1781886874454,"version":"3.54.5"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2017YFB1002102"],"award-info":[{"award-number":["2017YFB1002102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61603252"],"award-info":[{"award-number":["61603252"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["U1736202"],"award-info":[{"award-number":["U1736202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/taslp.2018.2851155","type":"journal-article","created":{"date-parts":[[2018,6,27]],"date-time":"2018-06-27T18:54:20Z","timestamp":1530125660000},"page":"2002-2014","source":"Crossref","is-referenced-by-count":56,"title":["Investigating Raw Wave Deep Neural Networks for End-to-End Speaker Spoofing Detection"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4330-8980","authenticated-orcid":false,"given":"Heinrich","family":"Dinkel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7102-9826","authenticated-orcid":false,"given":"Kai","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462575"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966240"},{"key":"ref33","first-page":"1","article-title":"Asvspoof 2015: Automatic speaker verification\n spoofing and countermeasures challenge evaluation plan","author":"wu","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2684705"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2682788"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472636"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2687041"},{"key":"ref36","first-page":"2067","article-title":"Spoofing detection with DNN and one-class\n SVM for the ASVspoof 2015 challenge","author":"villalba","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref35","first-page":"2097","article-title":"Robust deep feature for spoofing detection—The SJTU system\n for ASVspoof 2015 challenge","author":"chen","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953080"},{"key":"ref60","first-page":"317","article-title":"Time-frequency convolutional networks for robust speech recognition","author":"horacio","year":"2015","journal-title":"Proc IEEE Workshop Autom Speech Recog Underst"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2014.2349158"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2015.7358783"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396517"},{"key":"ref28","first-page":"27","article-title":"Audio replay attack detection using high-frequency\n features","author":"witkowski","year":"2017","journal-title":"Proc Conf Int Speech Commun Assoc"},{"key":"ref64","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2326991"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2692389"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2647199"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953185"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2013.6718948"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"283","DOI":"10.21437\/Odyssey.2016-41","article-title":"A new\n feature for automatic speaker verification anti-spoofing: Constant Q cepstral coefficients","volume":"45","author":"todisco","year":"2016","journal-title":"Odyssey"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2647202"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952516"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.230"},{"key":"ref25","first-page":"1709","article-title":"Unsupervised deep haar scattering on graphs","author":"chen","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref50","first-page":"818","article-title":"Visualizing and understanding convolutional networks","volume":"8689 lncs","author":"zeiler","year":"2014","journal-title":"Eur Conf Comput Vis in Lecture Notes Comput Sci (including subseries Lecture Notes Artif Intell Lecture Notes Bioinf )"},{"key":"ref51","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"ArXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref58","article-title":"Reasoning about entailment with neural attention","author":"rocktschel","year":"2015"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref56","article-title":"Exploring hierarchical speech representations with a deep convolutional neural network","author":"hau","year":"2011","journal-title":"Proc 11th U K Annu Workshop Comput Intell"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref54","first-page":"1026","article-title":"Delving deep into rectifiers: Surpassing human-level\n performance on imagenet classification","author":"he","year":"2016","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref53","first-page":"1","article-title":"Deep learning of representations: Looking forward","volume":"7978 lnai","author":"bengio","year":"2013","journal-title":"Int Conf Statistical Lang Speech Process in Lecture Notes Comput Sci"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.007"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref11","first-page":"1","article-title":"A study on spoofing attack in state-of-the-art speaker verification: The\n telephone speech case","author":"wu","year":"2012","journal-title":"Proc Asia Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref40","first-page":"4884","article-title":"Towards directly modeling raw speech signal for speaker verification using CNNS","author":"muckenhirn","year":"2018","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref12","first-page":"925","article-title":"Spoofing\n and countermeasures for automatic speaker verification","author":"evans","year":"2013","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref13","article-title":"Can a professional imitator fool a GMM-based speaker verification system?","author":"marithoz","year":"2005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1093\/ietfec\/E88-A.1.280"},{"key":"ref15","first-page":"2","article-title":"Detecting converted speech and\n natural speech for anti-spoofing attack in speaker recognition","author":"wu","year":"2012","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref16","first-page":"370","article-title":"Synthetic speech discrimination using pitch pattern statistics derived from image analysis","author":"de leon","year":"2012","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2016.7791200"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref19","first-page":"1700","article-title":"Integrated spoofing countermeasures and automatic speaker\n verification: An evaluation on ASVspoof 2015","author":"todisco","year":"2016","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref4","first-page":"117","article-title":"First attempt of boltzmann machines for\n speaker verification","author":"senoussaoui","year":"2012","journal-title":"Odyssey"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.840940"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889708"},{"key":"ref5","first-page":"185","article-title":"Multi-task\n learning for text-dependent speaker verification","author":"chen","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.07.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref49","article-title":"An i-vector extractor suitable for\n speaker recognition with both microphone and telephone speech","author":"senoussaoui","year":"2010","journal-title":"Odyssey"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2732162"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref45","first-page":"171","article-title":"End-to-end attention based text-dependent speaker verification","author":"zhang","year":"2017","journal-title":"Proc IEEE Workshop Spoken Lang Technol"},{"key":"ref48","first-page":"61","article-title":"Introducing i-vectors for joint anti-spoofing and speaker\n verification","author":"khoury","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1140"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2017.8272715"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178847"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8429900\/08398462.pdf?arnumber=8398462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T13:45:19Z","timestamp":1643204719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8398462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":66,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2851155","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}