{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T14:40:02Z","timestamp":1750171202834,"version":"3.40.4"},"publisher-location":"London","reference-count":107,"publisher":"Springer London","isbn-type":[{"type":"print","value":"9781447165231"},{"type":"electronic","value":"9781447165248"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-1-4471-6524-8_7","type":"book-chapter","created":{"date-parts":[[2014,8,29]],"date-time":"2014-08-29T15:09:12Z","timestamp":1409324952000},"page":"125-146","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Speaker Recognition Anti-spoofing"],"prefix":"10.1007","author":[{"given":"Nicholas","family":"Evans","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomi","family":"Kinnunen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Federico","family":"Alegre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Phillip De","family":"Leon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,7,18]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Evans N, Kinnunen T, Yamagishi J (2013) Spoofing and countermeasures for automatic speaker verification. In: Proceedings of interspeech, annual conference of the international speech communication association, Lyon, France","DOI":"10.21437\/Interspeech.2013-288"},{"key":"7_CR2","unstructured":"Pelecanos J, Sridharan S (2001) Feature warping for robust speaker verification. In: Proceedings of Odyssey 2001: the speaker and language recognition workshop, Crete, Greece, pp 213\u2013218"},{"issue":"3\u20134","key":"7_CR3","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.specom.2005.02.018","volume":"46","author":"E Shriberg","year":"2005","unstructured":"Shriberg E, Ferrer L, Kajarekar S, Venkataraman A, Stolcke A (2005) Modeling prosodic feature sequences for speaker recognition. Speech Commun 46(3\u20134):455\u2013472","journal-title":"Speech Commun"},{"issue":"7","key":"7_CR4","doi-asserted-by":"publisher","first-page":"2095","DOI":"10.1109\/TASL.2007.902758","volume":"15","author":"N Dehak","year":"2007","unstructured":"Dehak N, Kenny P, Dumouchel P (2007) Modeling prosodic features with joint factor analysis for speaker verification. IEEE Trans Audio Speech Lang Process 15(7):2095\u20132103","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Siddiq S, Kinnunen T, Vainio M, Werner S (2012) Intonational speaker verification: a study on parameters and performance under noisy conditions. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), Kyoto, Japan, pp 4777\u20134780","DOI":"10.1109\/ICASSP.2012.6288987"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Kockmann M, Ferrer L, Burget L, C\u011brnock\u00fd J (2011) i-vector fusion of prosodic and cepstral features for speaker verification. In: Proceedings of interspeech, annual conference of the international speech communication association, Florence, Italy, pp 265\u2013268","DOI":"10.21437\/Interspeech.2011-57"},{"issue":"1","key":"7_CR7","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.specom.2009.08.009","volume":"52","author":"T Kinnunen","year":"2010","unstructured":"Kinnunen T, Li H (2010) An overview of text-independent speaker recognition: from features to supervectors. Speech Commun 52(1):12\u201340","journal-title":"Speech Commun"},{"key":"7_CR8","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/89.365379","volume":"3","author":"D Reynolds","year":"1995","unstructured":"Reynolds D, Rose R (1995) Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans Speech Audio Process 3:72\u201383","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"1","key":"7_CR9","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds DA, Quatieri TF, Dunn RB (2000) Speaker verification using adapted Gaussian mixture models. Digital Signal Process 10(1):19\u201341","journal-title":"Digital Signal Process"},{"issue":"5","key":"7_CR10","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1109\/LSP.2006.870086","volume":"13","author":"WM Campbell","year":"2006","unstructured":"Campbell WM, Sturim DE, Reynolds DA (2006) Support vector machines using GMM supervectors for speaker verification. IEEE Signal Process Lett 13(5):308\u2013311","journal-title":"IEEE Signal Process Lett"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Solomonoff A, Campbell W, Boardman I (2005) Advances in channel compensation for SVM speaker recognition. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), pp 629\u2013632, Philadelphia, USA","DOI":"10.1109\/ICASSP.2005.1415192"},{"issue":"7","key":"7_CR12","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1109\/TASL.2007.902499","volume":"15","author":"L Burget","year":"2007","unstructured":"Burget L, Mat\u011bjka P, Schwarz P, Glembek O, \u010cernock\u00fd J (2007) Analysis of feature extraction and channel compensation in a GMM speaker recognition system. IEEE Trans Audio Speech Lang Process 15(7):1979\u20131986","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Hatch AO, Kajarekar S, Stolcke A (2006) Within-class covariance normalization for svm-based speaker recognition. In: Proceedings of IEEE international conference on spoken language process (ICSLP), pp 1471\u20131474","DOI":"10.21437\/Interspeech.2006-183"},{"key":"7_CR14","unstructured":"Kenny, P (2006) Joint factor analysis of speaker and session variability: theory and algorithms. technical report CRIM-06\/08-14"},{"issue":"4","key":"7_CR15","doi-asserted-by":"publisher","first-page":"1448","DOI":"10.1109\/TASL.2007.894527","volume":"15","author":"P Kenny","year":"2007","unstructured":"Kenny P, Boulianne G, Ouellet P, Dumouchel P (2007) Speaker and session variability in GMM-based speaker verification. IEEE Trans Audio Speech Lang Process 15(4):1448\u20131460","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"5","key":"7_CR16","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1109\/TASL.2008.925147","volume":"16","author":"P Kenny","year":"2008","unstructured":"Kenny P, Ouellet P, Dehak N, Gupta V, Dumouchel P (2008) A study of inter-speaker variability in speaker verification. IEEE Trans Audio Speech Lang Process 16(5):980\u2013988","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"4","key":"7_CR17","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak N, Kenny P, Dehak R, Dumouchel P, Ouellet P (2011) Front-end factor analysis for speaker verification. IEEE Trans Audio Speech Lang Process 19(4):788\u2013798","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"1","key":"7_CR18","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1109\/TPAMI.2011.104","volume":"34","author":"P Li","year":"2012","unstructured":"Li P, Fu Y, Mohammed U, Elder JH, Prince SJ (2012) Probabilistic models for inference about identity. IEEE Trans Pattern Anal Mach Intell 34(1):144\u2013157","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Garcia-Romero D, Espy-Wilson CY (2011) Analysis of i-vector length normalization in speaker recognition systems. In: Proceedings of interspeech, annual conference of the international speech communication association, Florence, Italy, pp 249\u2013252","DOI":"10.21437\/Interspeech.2011-53"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Kinnunen T, Wu ZZ, Lee KA, Sedlak F, Chng ES, Li H (2012) Vulnerability of speaker verification systems against voice conversion spoofing attacks: the case of telephone speech. In: Proceedings of IEEE international conference on acoustics speech and signal process (ICASSP), pp 4401\u20134404","DOI":"10.1109\/ICASSP.2012.6288895"},{"key":"7_CR21","unstructured":"Saeidi R et al (2013) I4U submission to NIST SRE 2012: a large-scale collaborative effort for noise-robust speaker verification. In: Proceedings of interspeech, annual conference of the international speech communication association, Lyon, France"},{"issue":"7","key":"7_CR22","doi-asserted-by":"publisher","first-page":"2072","DOI":"10.1109\/TASL.2007.902870","volume":"15","author":"N Br\u00fcmmer","year":"2007","unstructured":"Br\u00fcmmer N, Burget L, \u010cernock\u00fd J, Glembek O, Gr\u00e9zl F, Karafi\u00e1t M, Leeuwen D, Mat\u011bjka P, Schwartz P, Strasheim A (2007) Fusion of heterogeneous speaker recognition systems in the STBU submission for the NIST speaker recognition evaluation 2006. IEEE Trans Audio Speech Lang Process 15(7):2072\u20132084","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"8","key":"7_CR23","doi-asserted-by":"publisher","first-page":"1622","DOI":"10.1109\/TASL.2013.2256895","volume":"21","author":"V Hautam\u00e4ki","year":"2013","unstructured":"Hautam\u00e4ki V, Kinnunen T, Sedl\u00e1k F, Lee KA, Ma B, Li H (2013) Sparse classifier fusion for speaker verification. IEEE Trans Audio Speech Lang Process 21(8):1622\u20131631","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Akhtar Z, Fumera G, Marcialis GL, Roli F (2012) Evaluation of serial and parallel multibiometric systems under spoong attacks. In: Proceedings of 5th Int. Conference on biometrics (ICB 2012), pp 283\u2013288, New Delhi, India","DOI":"10.1109\/BTAS.2012.6374590"},{"key":"7_CR25","unstructured":"Lau YW, Wagner M, Tran D (2004) Vulnerability of speaker verification to voice mimicking. In: Proceedings of 2004 international symposium on Intelligent multimedia, video and speech processing, 2004. IEEE, pp 145\u2013148"},{"key":"7_CR26","first-page":"907","volume-title":"Knowledge-based intelligent information and engineering systems","author":"Y Lau","year":"2005","unstructured":"Lau Y, Tran D, Wagner M (2005) Testing voice mimicry with the yoho speaker verification corpus. Knowledge-based intelligent information and engineering systems. Springer, Berlin, p 907"},{"key":"7_CR27","unstructured":"Mari\u00e9thoz J, Bengio S (2005) Can a professional imitator fool a GMM-based speaker verification system? IDIAP Research Report 05\u201361"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Eriksson A, Wretling P (1997) How flexible is the human voice?\u2014a case study of mimicry. In: Proceedings of Eurospeech, ESCA European conference on speech communication and technology, pp 1043\u20131046. http:\/\/www.ling.gu.se\/anders\/papers\/a1008.pdf","DOI":"10.21437\/Eurospeech.1997-363"},{"key":"7_CR29","unstructured":"Zetterholm E, Blomberg M, Elenius D (2004) A comparison between human perception and a speaker verification system score of a voice imitation. In: Proceedings of tenth australian international conference on speech science and technology, Macquarie University, Sydney, Australia, pp 393\u2013397"},{"key":"7_CR30","unstructured":"Farr\u00fas M, Wagner M, Anguita J, Hernando J (2008) How vulnerable are prosodic features to professional imitators? In: The speaker and language recognition workshop (Odyssey 2008), Stellenbosch, South Africa"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Kitamura T (2008) Acoustic analysis of imitated voice produced by a professional impersonator. In: Proceedings of interspeech, annual conference of the international speech communication association, Brisbane, Australia, pp 813\u2013816","DOI":"10.21437\/Interspeech.2008-248"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Perrot P, Aversano G, Blouet R, Charbit M, Chollet G (2005) Voice forgery using ALISP: indexation in a client memory. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), vol 1, pp 17\u201320","DOI":"10.1109\/ICASSP.2005.1415039"},{"key":"7_CR33","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.21437\/Eurospeech.1999-283","volume":"3","author":"J Lindberg","year":"1999","unstructured":"Lindberg J, Blomberg M et al (1999) Vulnerability in speaker verification-a study of technical impostor techniques. Proc Eur Conf speech Commun Technol 3:1211\u20131214","journal-title":"Proc Eur Conf speech Commun Technol"},{"key":"7_CR34","unstructured":"Villalba J, Lleida E (2010) Speaker verification performance degradation against spoofing and tampering attacks. In: FALA 10 workshop, pp 131\u2013134"},{"key":"7_CR35","first-page":"1708","volume":"4","author":"ZF Wang","year":"2011","unstructured":"Wang ZF, Wei G, He QH (2011) Channel pattern noise based playback attack detection algorithm for speaker recognition. Int Conf Mach Learn Cybern (ICMLC) 4:1708\u20131713","journal-title":"Int Conf Mach Learn Cybern (ICMLC)"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Shang W, Stevenson M (2010) Score normalization in playback attack detection. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), pp 1678\u20131681","DOI":"10.1109\/ICASSP.2010.5495503"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Villalba J, Lleida E (2011) Preventing replay attacks on speaker verification systems. In: Proceedings of the IEEE international carnahan conference on security technology, (ICCST) 2011, pp 1\u20138","DOI":"10.1109\/CCST.2011.6095943"},{"key":"7_CR38","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1121\/1.383940","volume":"67","author":"DH Klatt","year":"1980","unstructured":"Klatt DH (1980) Software for a cascade\/parallel formant synthesizer. J Acoust Soc Am 67:971\u2013995","journal-title":"J Acoust Soc Am"},{"key":"7_CR39","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1016\/0167-6393(90)90021-Z","volume":"9","author":"E Moulines","year":"1990","unstructured":"Moulines E, Charpentier F (1990) Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones. Speech Commun 9:453\u2013467","journal-title":"Speech Commun"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Hunt A, Black AW (1996) Unit selection in a concatenative speech synthesis system using a large speech database. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), pp 373\u2013376","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Breen A, Jackson P (1998) A phonologically motivated method of selecting nonuniform units. In: Proceedings of IEEE international conference on spoken language process (ICSLP), pp 2735\u20132738","DOI":"10.21437\/ICSLP.1998-48"},{"key":"7_CR42","doi-asserted-by":"crossref","unstructured":"Donovan RE, Eide EM (1998) The IBM trainable speech synthesis system. In: Proceedings of IEEE international conference on spoken language process (ICSLP), pp 1703\u20131706","DOI":"10.21437\/ICSLP.1998-10"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Beutnagel B, Conkie A, Schroeter J, Stylianou Y, Syrdal A (1999) The AT&T next-gen TTS system. In: Proceedings of joint ASA, EAA and DAEA meeting, pp 15\u201319","DOI":"10.1121\/1.424924"},{"key":"7_CR44","doi-asserted-by":"crossref","unstructured":"Coorman G, Fackrell J, Rutten P, Coile B (2000) Segment selection in the L & H realspeak laboratory TTS system. In: Proceedings of international conference on speech and language processing, pp 395\u2013398","DOI":"10.21437\/ICSLP.2000-291"},{"key":"7_CR45","doi-asserted-by":"crossref","unstructured":"Yoshimura T, Tokuda K, Masuko T, Kobayashi T, Kitamura T (1999) Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis. In: Proceedings of Eurospeech, ESCA European conference on speech communication and technology, pp 2347\u20132350","DOI":"10.21437\/Eurospeech.1999-513"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Ling ZH, Wu YJ, Wang YP, Qin L, Wang RH (2006) USTC system for blizzard challenge 2006 an improved HMM-based speech synthesis method. In: Proceedings of the blizzard challenge workshop","DOI":"10.21437\/Blizzard.2006-6"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Black AW (2006) CLUSTERGEN: a statistical parametric synthesizer using trajectory modeling. In: Proceedings of interspeech, annual conference of the international speech communication association, pp 1762\u20131765","DOI":"10.21437\/Interspeech.2006-488"},{"issue":"1","key":"7_CR48","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1093\/ietisy\/e90-1.1.325","volume":"E90\u2013D","author":"H Zen","year":"2007","unstructured":"Zen H, Toda T, Nakamura M, Tokuda K (2007) Details of the Nitech HMM-based speech synthesis system for the Blizzard Challenge 2005. IEICE Trans Inf Syst E90\u2013D(1):325\u2013333","journal-title":"IEICE Trans Inf Syst"},{"issue":"11","key":"7_CR49","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","volume":"51","author":"H Zen","year":"2009","unstructured":"Zen H, Tokuda K, Black AW (2009) Statistical parametric speech synthesis. Speech Communication 51(11):1039\u20131064. doi:10.1016\/j.specom.2009.04.004","journal-title":"Speech Communication"},{"issue":"1","key":"7_CR50","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/TASL.2008.2006647","volume":"17","author":"J Yamagishi","year":"2009","unstructured":"Yamagishi J, Kobayashi T, Nakano Y, Ogata K, Isogai J (2009) Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm. IEEE Trans Speech Audio Lang Process 17(1):66\u201383","journal-title":"IEEE Trans Speech Audio Lang Process"},{"key":"7_CR51","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1006\/csla.1995.0010","volume":"9","author":"CJ Leggetter","year":"1995","unstructured":"Leggetter CJ, Woodland PC (1995) Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput Speech Lang 9:171\u2013185","journal-title":"Comput Speech Lang"},{"key":"7_CR52","unstructured":"Woodland PC (2001) Speaker adaptation for continuous density HMMs: A review. In: Proceedings of ISCA workshop on adaptation methods for speech recognition, p 119"},{"key":"7_CR53","doi-asserted-by":"publisher","unstructured":"Foomany F, Hirschfield A, Ingleby M (2009) Toward a dynamic framework for security evaluation of voice verification systems. In: IEEE toronto international conference on science and technology for humanity (TIC-STH), pp 22\u201327. doi:10.1109\/TIC-STH.2009.5444499","DOI":"10.1109\/TIC-STH.2009.5444499"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Masuko T, Hitotsumatsu T, Tokuda K, Kobayashi T (1999) On the security of HMM-based speaker verification systems against imposture using synthetic speech. In: Proceedings of Eurospeech, ESCA European conference on speech communication and technology","DOI":"10.21437\/Eurospeech.1999-286"},{"issue":"1\u20132","key":"7_CR55","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/0167-6393(95)00011-C","volume":"17","author":"T Matsui","year":"1995","unstructured":"Matsui T, Furui S (1995) Likelihood normalization for speaker verification using a phoneme- and speaker-independent model. Speech Commun 17(1\u20132):109\u2013116","journal-title":"Speech Commun"},{"key":"7_CR56","unstructured":"Masuko T, Tokuda K, Kobayashi T, Imai S (1996) Speech synthesis using HMMs with dynamic features. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP)"},{"key":"7_CR57","unstructured":"Masuko T, Tokuda K, Kobayashi T, Imai S (1997) Voice characteristics conversion for HMM-based speech synthesis system. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP)"},{"issue":"8","key":"7_CR58","doi-asserted-by":"publisher","first-page":"2280","DOI":"10.1109\/TASL.2012.2201472","volume":"20","author":"PL De Leon","year":"2012","unstructured":"De Leon PL, Pucher M, Yamagishi J, Hernaez I, Saratxaga I (2012) Evaluation of speaker verification security and detection of HMM-based synthetic speech. IEEE Trans Audio Speech Lang Process 20(8):2280\u20132290. doi:10.1109\/TASL.2012.2201472","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"7_CR59","unstructured":"Galou, G (2011) Synthetic voice forgery in the forensic context: a short tutorial. In: Forensic speech and audio analysis working group (ENFSI-FSAAWG), pp 1\u20133"},{"key":"7_CR60","doi-asserted-by":"crossref","unstructured":"Satoh T, Masuko T, Kobayashi T, Tokuda K (2001) A robust speaker verification system against imposture using an HMM-based speech synthesis system. In: Proceedings of Eurospeech, ESCA European conference on speech technology","DOI":"10.21437\/Eurospeech.2001-239"},{"key":"7_CR61","doi-asserted-by":"publisher","unstructured":"Chen LW, Guo W, Dai LR (2010) Speaker verification against synthetic speech. In: Proceedings of 7th international symposium on chinese spoken language processing (ISCSLP), pp 309\u2013312 (29 Nov\u20133 Dec 2010). doi:10.1109\/ISCSLP.2010.5684887","DOI":"10.1109\/ISCSLP.2010.5684887"},{"key":"7_CR62","unstructured":"Quatieri TF (2002) Discrete-time speech signal processing principles and practice. Prentice-hall, Inc"},{"key":"7_CR63","doi-asserted-by":"crossref","unstructured":"Wu Z, Chng ES, Li H (2012) Detecting converted speech and natural speech for anti-spoofing attack in speaker recognition. In: Proceedings of interspeech, annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2012-465"},{"issue":"1","key":"7_CR64","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1093\/ietfec\/E88-A.1.280","volume":"88","author":"A Ogihara","year":"2005","unstructured":"Ogihara A, Unno H, Shiozakai A (2005) Discrimination method of synthetic speech using pitch frequency against synthetic speech falsification. IEICE Trans Fundam Electron Commun Comput Sci 88(1):280\u2013286","journal-title":"IEICE Trans Fundam Electron Commun Comput Sci"},{"key":"7_CR65","doi-asserted-by":"crossref","unstructured":"De Leon PL, Stewart B, Yamagishi J (2012) Synthetic speech discrimination using pitch pattern statistics derived from image analysis. In: Proceedings of interspeech, annual conference of the international speech communication association, Portland, Oregon, USA","DOI":"10.21437\/Interspeech.2012-135"},{"key":"7_CR66","doi-asserted-by":"crossref","unstructured":"Stylianou Y (2009) Voice transformation: a survey. In: Proceedings of IEEE international conference on acoustics speech and signal process (ICASSP), pp 3585\u20133588","DOI":"10.1109\/ICASSP.2009.4960401"},{"key":"7_CR67","unstructured":"Pellom BL, Hansen JH (1999) An experimental study of speaker verification sensitivity to computer voice-altered imposters. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), vol 2, pp 837\u2013840"},{"key":"7_CR68","doi-asserted-by":"crossref","unstructured":"Abe M, Nakamura S, Shikano K, Kuwabara H (1988) Voice conversion through vector quantization. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), pp 655\u2013658","DOI":"10.1109\/ICASSP.1988.196671"},{"issue":"3","key":"7_CR69","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/S0167-6393(99)00015-1","volume":"28","author":"LM Arslan","year":"1999","unstructured":"Arslan LM (1999) Speaker transformation algorithm using segmental codebooks (STASC). Speech Commun 28(3):211\u2013226","journal-title":"Speech Commun"},{"key":"7_CR70","doi-asserted-by":"crossref","unstructured":"Kain A, Macon MW (1998) Spectral voice conversion for text-to-speech synthesis. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), vol 1, pp 285\u2013288","DOI":"10.1109\/ICASSP.1998.674423"},{"issue":"2","key":"7_CR71","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/89.661472","volume":"6","author":"Y Stylianou","year":"1998","unstructured":"Stylianou Y, Capp\u00e9 O, Moulines E (1998) Continuous probabilistic transform for voice conversion. IEEE Trans Speech Audio Process 6(2):131\u2013142","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"8","key":"7_CR72","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","volume":"15","author":"T Toda","year":"2007","unstructured":"Toda T, Black AW, Tokuda K (2007) Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory. IEEE Trans Audio Speech Lang Process 15(8):2222\u20132235","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"7_CR73","doi-asserted-by":"crossref","unstructured":"Popa V, Silen H, Nurminen J, Gabbouj M (2012) Local linear transformation for voice conversion. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), pp 4517\u20134520","DOI":"10.1109\/ICASSP.2012.6288922"},{"key":"7_CR74","doi-asserted-by":"crossref","unstructured":"Chen Y, Chu M, Chang E, Liu J, Liu R (2003) Voice conversion with smoothed GMM and MAP adaptation. In: Proceedings of Eurospeech, ESCA European conference on speech communication and technology, pp 2413\u20132416","DOI":"10.21437\/Eurospeech.2003-664"},{"key":"7_CR75","doi-asserted-by":"crossref","unstructured":"Hwang HT, Tsao Y, Wang HM, Wang YR, Chen SH (2012) A study of mutual information for GMM-based spectral conversion. In: Proceedings of Interspeech, annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2012-30"},{"issue":"5","key":"7_CR76","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1109\/TASL.2010.2041699","volume":"18","author":"E Helander","year":"2010","unstructured":"Helander E, Virtanen T, Nurminen J, Gabbouj M (2010) Voice conversion using partial least squares regression. IEEE Trans Audio Speech Lang Process 18(5):912\u2013921","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"7_CR77","doi-asserted-by":"crossref","unstructured":"Pilkington NC, Zen H, Gales MJ (2011) Gaussian process experts for voice conversion. In: Twelfth annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2011-691"},{"key":"7_CR78","doi-asserted-by":"crossref","unstructured":"Saito D, Yamamoto K, Minematsu N, Hirose K (2011) One-to-many voice conversion based on tensor representation of speaker space. In: Proceedings of Interspeech, annual conference of the international speech communication association, pp 653\u2013656","DOI":"10.21437\/Interspeech.2011-268"},{"issue":"2","key":"7_CR79","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1109\/TASL.2010.2049685","volume":"19","author":"H Zen","year":"2011","unstructured":"Zen H, Nankaku Y, Tokuda K (2011) Continuous stochastic feature mapping based on trajectory HMMs. IEEE Trans Audio Speech Lang Process 19(2):417\u2013430","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"12","key":"7_CR80","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1109\/LSP.2012.2225615","volume":"19","author":"Z Wu","year":"2012","unstructured":"Wu Z, Kinnunen T, Chng ES, Li H (2012) Mixture of factor analyzers using priors from non-parallel speech for voice conversion. IEEE Signal Process Lett 19(12):914\u2013917","journal-title":"IEEE Signal Process Lett"},{"issue":"6","key":"7_CR81","doi-asserted-by":"publisher","first-page":"1784","DOI":"10.1109\/TASL.2012.2188628","volume":"20","author":"D Saito","year":"2012","unstructured":"Saito D, Watanabe S, Nakamura A, Minematsu N (2012) Statistical voice conversion based on noisy channel model. IEEE Trans Audio Speech Lang Process 20(6):1784\u20131794","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"2","key":"7_CR82","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/0167-6393(94)00058-I","volume":"16","author":"M Narendranath","year":"1995","unstructured":"Narendranath M, Murthy HA, Rajendran S, Yegnanarayana B (1995) Transformation of formants for voice conversion using artificial neural networks. Speech commun 16(2):207\u2013216","journal-title":"Speech commun"},{"key":"7_CR83","doi-asserted-by":"crossref","unstructured":"Desai S, Raghavendra EV, Yegnanarayana B, Black AW, Prahallad K (2009) Voice conversion using artificial neural networks. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), pp 3893\u20133896","DOI":"10.1109\/ICASSP.2009.4960478"},{"issue":"18","key":"7_CR84","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1049\/el.2011.1851","volume":"47","author":"P Song","year":"2011","unstructured":"Song P, Bao Y, Zhao L, Zou C (2011) Voice conversion using support vector regression. Electron Lett 47(18):1045\u20131046","journal-title":"Electron Lett"},{"issue":"3","key":"7_CR85","doi-asserted-by":"publisher","first-page":"806","DOI":"10.1109\/TASL.2011.2165944","volume":"20","author":"E Helander","year":"2012","unstructured":"Helander E, Sil\u00e9n H, Virtanen T, Gabbouj M (2012) Voice conversion using dynamic kernel partial least squares regression. IEEE Trans Audio Speech Lang Process 20(3):806\u2013817","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"7_CR86","doi-asserted-by":"crossref","unstructured":"Wu Z, Chng ES, Li H (2013) Conditional restricted boltzmann machine for voice conversion. In: The first IEEE china summit and international conference on signal and information processing (ChinaSIP)","DOI":"10.1109\/ChinaSIP.2013.6625307"},{"key":"7_CR87","unstructured":"Sundermann D, Ney H (2003) VTLN-based voice conversion. In: Proceedings of the 3rd IEEE international symposium on signal processing and information technology, 2003. ISSPIT 2003, pp 556\u2013559"},{"issue":"5","key":"7_CR88","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1109\/TASL.2009.2038663","volume":"18","author":"D Erro","year":"2010","unstructured":"Erro D, Moreno A, Bonafonte A (2010) Voice conversion based on weighted frequency warping. IEEE Trans Audio Speech Lang Process 18(5):922\u2013931","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"3","key":"7_CR89","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1109\/TASL.2012.2227735","volume":"21","author":"D Erro","year":"2013","unstructured":"Erro D, Navas E, Hernaez I (2013) Parametric voice conversion based on bilinear frequency warping plus amplitude scaling. IEEE Trans Audio Speech Lang Process 21(3):556\u2013566","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"7_CR90","doi-asserted-by":"crossref","unstructured":"Gillet B, King S (2003) Transforming F0 contours. In: Proceedings of Eurospeech, ESCA European conference on speech communication and technology, pp 101\u2013104","DOI":"10.21437\/Eurospeech.2003-74"},{"issue":"4","key":"7_CR91","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1109\/TASL.2006.876112","volume":"14","author":"CH Wu","year":"2006","unstructured":"Wu CH, Hsia CC, Liu TH, Wang JF (2006) Voice conversion using duration-embedded bi-HMMs for expressive speech synthesis. IEEE Trans Audio Speech Lang Process 14(4):1109\u20131116","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"7_CR92","doi-asserted-by":"crossref","unstructured":"Helander EE, Nurminen J (2007) A novel method for prosody prediction in voice conversion. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), pp IV-509","DOI":"10.1109\/ICASSP.2007.366961"},{"key":"7_CR93","doi-asserted-by":"crossref","unstructured":"Wu ZZ, Kinnunen T, Chng ES, Li H (2010) Text-independent F0 transformation with non-parallel data for voice conversion. In: Eleventh annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2010-497"},{"key":"7_CR94","doi-asserted-by":"crossref","first-page":"111","DOI":"10.21437\/SpeechProsody.2008-26","volume":"2008","author":"D Lolive","year":"2008","unstructured":"Lolive D, Barbot N, Boeffard O (2008) Pitch and duration transformation with non-parallel data. Speech prosody 2008:111\u2013114","journal-title":"Speech prosody"},{"key":"7_CR95","doi-asserted-by":"crossref","unstructured":"Sundermann D, Hoge H, Bonafonte A, Ney H, Black A, Narayanan S (2006) Text-independent voice conversion based on unit selection. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), vol 1, pp I-I","DOI":"10.1109\/ICASSP.2006.1659962"},{"key":"7_CR96","doi-asserted-by":"crossref","unstructured":"Wu Z, Larcher A, Lee KA, Chng ES, Kinnunen T, Li H (2013) Vulnerability evaluation of speaker verication under voice conversion spoong: the effect of text constraints. In: Proceedings of interspeech, annual conference of the international speech communication association, Lyon, France","DOI":"10.21437\/Interspeech.2013-293"},{"key":"7_CR97","doi-asserted-by":"crossref","unstructured":"Matrouf D, Bonastre JF, Fredouille C (2006) Effect of speech transformation on impostor acceptance. In: Proceedings of IEEE international conference on acoustics, speech and signal process (ICASSP), vol 1, pp I-I","DOI":"10.1109\/ICASSP.2006.1660175"},{"key":"7_CR98","unstructured":"Alegre F, Vipperla R, Evans N, Fauve B (2012) On the vulnerability of automatic speaker recognition to spoofing attacks with artificial signals. In: Proceedings of EURASIP Euro signal processing conference (EUSIPCO)"},{"key":"7_CR99","unstructured":"Wu Z, Kinnunen T, Chng ES, Li H, Ambikairajah E (2012) A study on spoofing attack in state-of-the-art speaker verification: the telephone speech case. In: Signal and information processing association annual summit and conference (APSIPA ASC), 2012 Asia-Pacific, pp 1\u20135"},{"key":"7_CR100","doi-asserted-by":"crossref","unstructured":"De Leon PL, Hernaez I, Saratxaga I, Pucher M, Yamagishi J (2011) Detection of synthetic speech for the problem of imposture. In: Proceedings of IEEE international conference on acoustic, speech and signal process (ICASSP), pp 4844\u20134847, Dallas, USA","DOI":"10.1109\/ICASSP.2011.5947440"},{"key":"7_CR101","doi-asserted-by":"crossref","unstructured":"Alegre F, Vipperla R, Evans N, et al (2012) Spoofing countermeasures for the protection of automatic speaker recognition systems against attacks with artificial signals. In: Proceedings of interspeech, annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2012-462"},{"key":"7_CR102","doi-asserted-by":"crossref","unstructured":"Alegre F, Amehraye A, Evans N (2013) Spoofing countermeasures to protect automatic speaker verification from voice conversion. In: Proceedings of IEEE international conference on acoustic, speech and signal process (ICASSP)","DOI":"10.1109\/ICASSP.2013.6638222"},{"key":"7_CR103","doi-asserted-by":"crossref","unstructured":"Wu Z, Xiao X, Chng ES, Li H (2013) Synthetic speech detection using temporal modulation feature. In: Proceedings of IEEE international conference on acoustic, speech and signal process (ICASSP)","DOI":"10.1109\/ICASSP.2013.6639067"},{"key":"7_CR104","doi-asserted-by":"crossref","unstructured":"Alegre F, Vipperla R, Amehraye A, Evans N (2013) A new speaker verification spoofing countermeasure based on local binary patterns. In: Proceedings of interspeech, annual conference of the international speech communication association, Lyon, France","DOI":"10.21437\/Interspeech.2013-291"},{"key":"7_CR105","doi-asserted-by":"crossref","unstructured":"Hautamki RG, Kinnunen T, Hautamki V, Leino T, Laukkanen AM (2013) I-vectors meet imitators: on vulnerability of speaker verification systems against voice mimicry. In: Proceedings of interspeech, annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2013-289"},{"key":"7_CR106","doi-asserted-by":"crossref","unstructured":"Martin A, Doddington G, Kamm T, Ordowski M, Przybocki M (1997) The DET curve in assessment of detection task performance. In: Proceedings of Eurospeech, ESCA European conference on speech communication and technology, pp 1895\u20131898","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"7_CR107","doi-asserted-by":"crossref","unstructured":"Alegre F, Amehraye A, Evans N (2013) A one-class classification approach to generalised speaker verification spoofing countermeasures using local binary patterns. In: Proceedings of international conference on biometrics: theory, applications and systems (BTAS), Washington DC, USA","DOI":"10.1109\/BTAS.2013.6712706"}],"container-title":["Advances in Computer Vision and Pattern Recognition","Handbook of Biometric Anti-Spoofing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4471-6524-8_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T11:51:24Z","timestamp":1746359484000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-4471-6524-8_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9781447165231","9781447165248"],"references-count":107,"URL":"https:\/\/doi.org\/10.1007\/978-1-4471-6524-8_7","relation":{},"ISSN":["2191-6586","2191-6594"],"issn-type":[{"type":"print","value":"2191-6586"},{"type":"electronic","value":"2191-6594"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"18 July 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}