{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:07:34Z","timestamp":1774627654924,"version":"3.50.1"},"reference-count":68,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Programmatic Grant","award":["A1687b0033"],"award-info":[{"award-number":["A1687b0033"]}]},{"name":"Advanced Manufacturing and Engineering domain"},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG-100E-2018-006"],"award-info":[{"award-number":["AISG-100E-2018-006"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Human-Robot Interaction Phase 1","award":["1922500054"],"award-info":[{"award-number":["1922500054"]}]},{"name":"National Research Foundation, Prime Minister's Office, Singapore"},{"name":"National Robotics Programme"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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":[[2021]]},"DOI":"10.1109\/taslp.2021.3060810","type":"journal-article","created":{"date-parts":[[2021,2,22]],"date-time":"2021-02-22T23:54:15Z","timestamp":1614038055000},"page":"1065-1078","source":"Crossref","is-referenced-by-count":47,"title":["Modified Magnitude-Phase Spectrum Information for Spoofing Detection"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4954-8398","authenticated-orcid":false,"given":"Jichen","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongji","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1332-3357","authenticated-orcid":false,"given":"Rohan Kumar","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1023","article-title":"The DKU replay detection system for the ASVspoof 2019 challenge on data augmentation, feature representation, clssifier and fusion","author":"cai","year":"0","journal-title":"Proc 20th Annu Conf Int Speech Commun Assoc"},{"key":"ref38","first-page":"1078","article-title":"Deep residual neural networks for audio spoofing detection","author":"alzanto","year":"0","journal-title":"Proc 20th Annu Conf Int Speech Commun Assoc"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2684705"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2771947"},{"key":"ref31","first-page":"114","article-title":"Improved closed set text-independent speaker identification by combining MFCC with evidence from flipped filter banks","volume":"4","author":"chakroborty","year":"2007","journal-title":"Int J Signal Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638975"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2170"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1768"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-360"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2956589"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003792"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-44"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288895"},{"key":"ref64","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.02.005"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1693"},{"key":"ref29","first-page":"2087","article-title":"A comparison features for synthetic speech detection","author":"sahidullah","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref68","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":"10.1049\/el.2019.1264"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2946897"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1887"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2851155"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2732162"},{"key":"ref25","first-page":"1018","article-title":"Long range acoustic and deep features perspective on ASVspoof","author":"das","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2526653"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2279"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1794"},{"key":"ref58","first-page":"540","article-title":"Replay detection using CQT-based modified group delay feature and ResNeWt network in ASVspoof","author":"cheng","year":"0","journal-title":"Proc Asia Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2120"},{"key":"ref56","first-page":"1043","article-title":"IIIT-H spoofing countermeasures for automatic speaker verification spoofing and countermesures challenge 2019","author":"alluri","year":"0","journal-title":"Proc 20th Annu Conf Int Speech Commun Assoc"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"key":"ref54","first-page":"6599","article-title":"An ensemble based approcah for generalized detection of spoofing attack to automatic speaker recognizers","author":"monteiro","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053086"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1049\/el.2018.0739"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2950099"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3040523"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1991"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2723721"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2910637"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.05.002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.002"},{"key":"ref17","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 Annu Conf Int Speech Commun Assoc"},{"key":"ref18","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 Annu Conf Int Speech Commun Assoc"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-41"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3016498"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2928128"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1052"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2019EDL8115"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3011320"},{"key":"ref49","first-page":"2489","article-title":"Using group delay functions from all-pole models for speaker recognition","author":"rajan","year":"0","journal-title":"Proc 14th Annu Conf Int Speech Commun Assoc"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2165280"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659789"},{"key":"ref45","first-page":"22","article-title":"Spoof detection using source, instantaneous frequecny and cepstral features","author":"jelil","year":"0","journal-title":"Proc 18th Annu Conf Int Speech Commun Assoc"},{"key":"ref48","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 13th Annu Conf Int Speech Commun Assoc"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706672"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1819"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1255"},{"key":"ref44","first-page":"-68i","article-title":"The modified group delay function and its application to phone recognition","author":"murthy","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876858"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09360468.pdf?arnumber=9360468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:58Z","timestamp":1652194438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9360468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3060810","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}