{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T19:04:53Z","timestamp":1761419093277},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Department of Electronics and Information Technology, Government of India"},{"name":"TTS Phase-II and ASR Phase-II"},{"name":"Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1109\/jstsp.2017.2682788","type":"journal-article","created":{"date-parts":[[2017,3,16]],"date-time":"2017-03-16T01:49:22Z","timestamp":1489628962000},"page":"644-659","source":"Crossref","is-referenced-by-count":17,"title":["Significance of Source\u2013Filter Interaction for Classification of Natural vs. Spoofed Speech"],"prefix":"10.1109","volume":"11","author":[{"given":"Tanvina B.","family":"Patel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"261","article-title":"Concatenative speech synthesis using a harmonic plus noise model","author":"stylianou","year":"0","journal-title":"Proc ESCA\/IEEE Workshop Speech Synthesis"},{"key":"ref38","first-page":"1","article-title":"Aperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system STRAIGHT","author":"kawahara","year":"0","journal-title":"Proc 7th Int Workshop Models Anal Vocal Emissions Biomed Appl"},{"key":"ref33","first-page":"119","article-title":"The LF-model revisited. Transformations and frequency domain analysis","volume":"36","author":"fant","year":"1995","journal-title":"KTH Quaterly Progress Status Rep"},{"key":"ref32","first-page":"1","article-title":"A four-parameter model of glottal flow","volume":"26","author":"fant","year":"1985","journal-title":"KTH Quaterly Progress Status Rep"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1972.tb02651.x"},{"key":"ref30","author":"morse","year":"1987","journal-title":"Theoretical Acoustics"},{"key":"ref37","first-page":"2263","article-title":"Mixed excitation for HMM-based speech synthesis","author":"yoshimura","year":"0","journal-title":"Proc Int Speech Commun Assoc (Interspeech)"},{"key":"ref36","first-page":"2347","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis","author":"yoshimura","year":"0","journal-title":"Proc European conf speech process technology"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045239"},{"key":"ref34","article-title":"HMM-based speech synthesis using an acoustic glottal source model","author":"cabral","year":"2010"},{"key":"ref60","first-page":"1895","article-title":"The DET curve in assessment of detection task performance","author":"martin","year":"0","journal-title":"Proc European conf speech process technology"},{"key":"ref62","article-title":"Spoofing detection under noisy conditions: A preliminary investigation and an initial database","author":"tian","year":"2016"},{"key":"ref61","year":"0"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.002"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.007"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-668"},{"key":"ref29","author":"quatieri","year":"2012","journal-title":"Discrete-Time Speech Signal Processing Principles and Practice"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1002"},{"key":"ref22","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 Int Speech Commun Assoc (Interspeech)"},{"key":"ref21","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 Int Speech Commun Assoc (Interspeech)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SPLIM.2016.7528399"},{"key":"ref23","first-page":"2087","article-title":"A comparison of features for synthetic speech detection","author":"sahidullah","year":"0","journal-title":"Proc Int Speech Commun Assoc (Interspeech)"},{"key":"ref26","first-page":"2097","article-title":"Robust deep feature for spoofing detection—The SJTU system for ASVspoof 2015 challenge","author":"chen","year":"0","journal-title":"Proc Int Speech Commun Assoc (Interspeech)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-41"},{"key":"ref50","first-page":"143","article-title":"Exploiting time and frequency domain measures for precise voice source parameterisation","author":"kane","year":"0","journal-title":"Proc Speech Prosody"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-743"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2647201"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-015-9273-9"},{"key":"ref57","article-title":"Voice_Analysis_Toolkit: A set of MATLAB codes for carrying out glottal source and voice quality analysis","author":"kane","year":"2013"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2004526"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(92)90005-R"},{"key":"ref54","first-page":"1","article-title":"The blizzard challenge 2012","author":"king","year":"0","journal-title":"Proc Int Speech Commun Assoc (Interspeech)"},{"key":"ref53","article-title":"Blizzard Challenge","year":"2016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.04.001"},{"key":"ref10","first-page":"2037","article-title":"ASVspoof 2015: The first automatic speaker verification spoofing and countermeasures challenge","author":"wu","year":"0","journal-title":"Proc Int Speech Commun Assoc (Interspeech)"},{"key":"ref11","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 Int Speech Commun Assoc (Interspeech)"},{"key":"ref40","first-page":"1043","article-title":"Mel-generalized cepstral analysis-a unified approach to speech spectral estimation","author":"tokuda","year":"0","journal-title":"Proc Int Conf Spoken Lang Process (ICSLP)"},{"key":"ref12","first-page":"2042","article-title":"The AHOLAB RPS SSD spoofing challenge 2015 submission","author":"sanchez","year":"0","journal-title":"Proc Int Speech Commun Assoc (Interspeech)"},{"key":"ref13","first-page":"2092","article-title":"Relative phase information for detecting human speech and spoofed speech","author":"wang","year":"0","journal-title":"Proc Int Speech Commun Assoc (Interspeech)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2015.2398812"},{"key":"ref15","first-page":"302","article-title":"Imposture using synthetic speech against speaker verification based on spectrum and pitch","author":"masuko","year":"0","journal-title":"Proc Int Conf Spoken Lang Process (ICSLP)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/ietfec\/E88-A.1.280"},{"key":"ref17","first-page":"370","article-title":"Synthetic speech discrimination using pitch patten statistics derived from image analysis","author":"de leon","year":"0","journal-title":"Proc Int Speech Commun Assoc (Interspeech)"},{"key":"ref18","first-page":"5105","article-title":"Effectiveness of fundamental frequency (F0) and strength of excitation (SoE) for spoofed speech detection","author":"patel","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref19","first-page":"2077","article-title":"Spoofing countermeasure based on analysis of linear prediction error","author":"janicki","year":"0","journal-title":"Proc Int Speech Commun Assoc (Interspeech)"},{"key":"ref4","first-page":"227","article-title":"An HMM-based speech synthesis system applied to English","author":"tokuda","year":"0","journal-title":"Proc IEEE Workshop Speech Synthesis"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1109\/TPAMI.2011.104","article-title":"Probabilistic models for inference about identity","volume":"34","author":"li","year":"2012","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ODYSSEY.2006.248128"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543214"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178810"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1121\/1.2832337"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2616543"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(82)90015-2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1121\/1.2832339"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00015-1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415037"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/89.784109"},{"key":"ref43","article-title":"Modeling of the glottal flow derivative waveform with application to speaker identification","author":"plumpe","year":"1997"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/7927513\/07879263.pdf?arnumber=7879263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:14:15Z","timestamp":1642004055000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7879263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":63,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2017.2682788","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6]]}}}