{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T14:20:00Z","timestamp":1726410000238},"publisher-location":"Cham","reference-count":201,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319926261"},{"type":"electronic","value":"9783319926278"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-319-92627-8_15","type":"book-chapter","created":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T13:02:36Z","timestamp":1546347756000},"page":"321-361","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Introduction to Voice Presentation Attack Detection and Recent Advances"],"prefix":"10.1007","author":[{"given":"Md","family":"Sahidullah","sequence":"first","affiliation":[]},{"given":"H\u00e9ctor","family":"Delgado","sequence":"additional","affiliation":[]},{"given":"Massimiliano","family":"Todisco","sequence":"additional","affiliation":[]},{"given":"Tomi","family":"Kinnunen","sequence":"additional","affiliation":[]},{"given":"Nicholas","family":"Evans","sequence":"additional","affiliation":[]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[]},{"given":"Kong-Aik","family":"Lee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,2]]},"reference":[{"issue":"1","key":"15_CR1","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.specom.2009.08.009","volume":"52","author":"Tomi 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. https:\/\/doi.org\/10.1016\/j.specom.2009.08.009 . http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167639309001289","journal-title":"Speech Communication"},{"issue":"6","key":"15_CR2","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1109\/MSP.2015.2462851","volume":"32","author":"J Hansen","year":"2015","unstructured":"Hansen J, Hasan T (2015) Speaker recognition by machines and humans: a tutorial review. IEEE Signal Process Mag 32(6):74\u201399","journal-title":"IEEE Signal Process Mag"},{"key":"15_CR3","unstructured":"ISO\/IEC 30107: Information technology\u2014biometric presentation attack detection. International Organization for Standardization (2016)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Kinnunen T, Sahidullah M, Kukanov I, Delgado H, Todisco M, Sarkar A, Thomsen N, Hautam\u00e4ki V, Evans N, Tan ZH (2016) Utterance verification for text-dependent speaker recognition: a comparative assessment using the reddots corpus. In: Proceedings of Interspeech, pp 430\u2013434","DOI":"10.21437\/Interspeech.2016-1125"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Shang, W, Stevenson, M. (2010). Score normalization in playback attack detection. In: Proceedings of ICASSP. IEEE, pp 1678\u20131681","DOI":"10.1109\/ICASSP.2010.5495503"},{"key":"15_CR6","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.specom.2014.10.005","volume":"66","author":"Z Wu","year":"2015","unstructured":"Wu Z, Evans N, Kinnunen T, Yamagishi J, Alegre F, Li H (2015) Spoofing and countermeasures for speaker verification: a survey. Speech Commun 66:130\u2013153","journal-title":"Speech Commun"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Korshunov P, Marcel S, Muckenhirn H, Gon\u00e7alves A, Mello A, Violato R, Simoes F, Neto M, de\u00a0Angeloni AM, Stuchi J, Dinkel H, Chen N, Qian Y, Paul D, Saha G, Sahidullah M. (2016). Overview of BTAS 2016 speaker anti-spoofing competition. In: 2016 IEEE 8th international conference on biometrics theory, applications and systems (BTAS), pp 1\u20136 (2016)","DOI":"10.1109\/BTAS.2016.7791200"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Evans N, Kinnunen T, Yamagishi J, Wu Z, Alegre F, DeLeon P (2014) Speaker recognition anti-spoofing. In: Marcel S, Li, SZ, Nixon M (eds) Handbook of biometric anti-spoofing. Springer","DOI":"10.1007\/978-1-4471-6524-8_7"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Marcel S, Li SZ, Nixon M (eds) Handbook of biometric anti-spoofing: trusted biometrics under spoofing attacks. Springer (2014)","DOI":"10.1007\/978-1-4471-6524-8"},{"key":"15_CR10","unstructured":"Farr\u00fas\u00a0Cabeceran M, Wagner M, Erro D, Peric\u00e1s H (2010) Automatic speaker recognition as a measurement of voice imitation and conversion. The Int J Speech Lang Law 1(17):119\u2013142"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Perrot P, Aversano G, Chollet G (2007) Voice disguise and automatic detection: review and perspectives. Progress in nonlinear speech processing, pp. 101\u2013117","DOI":"10.1007\/978-3-540-71505-4_7"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Zetterholm E (2007) Detection of speaker characteristics using voice imitation. In: Speaker Classification II. Springer, pp 192\u2013205","DOI":"10.1007\/978-3-540-74122-0_16"},{"key":"15_CR13","unstructured":"Lau Y, 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":"15_CR14","doi-asserted-by":"crossref","unstructured":"Lau Y, Tran D, Wagner M (2005) Testing voice mimicry with the YOHO speaker verification corpus. In: International conference on knowledge-based and intelligent information and engineering systems. Springer, pp 15\u201321","DOI":"10.1007\/11554028_3"},{"key":"15_CR15","unstructured":"Mari\u00e9thoz J, Bengio S (2005) Can a professional imitator fool a GMM-based speaker verification system? Technical report, Idiap Research Institute"},{"key":"15_CR16","unstructured":"Panjwani S, Prakash A (2014) Crowdsourcing attacks on biometric systems. In: Symposium on usable privacy and security (SOUPS 2014), pp 257\u2013269"},{"key":"15_CR17","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.specom.2015.05.002","volume":"72","author":"R Hautam\u00e4ki","year":"2015","unstructured":"Hautam\u00e4ki R, Kinnunen T, Hautam\u00e4ki V, Laukkanen AM (2015) Automatic versus human speaker verification: the case of voice mimicry. Speech Commun 72:13\u201331","journal-title":"Speech Commun"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Ergunay S, Khoury E, Lazaridis A, Marcel S (2015) On the vulnerability of speaker verification to realistic voice spoofing. In: IEEE international conference on biometrics: theory, applications and systems, pp 1\u20138","DOI":"10.1109\/BTAS.2015.7358783"},{"key":"15_CR19","first-page":"1211","volume":"3","author":"J Lindberg","year":"1999","unstructured":"Lindberg J, Blomberg M (1999) Vulnerability in speaker verification-a study of technical impostor techniques. Proceedings of the European conference on speech communication and technology 3:1211\u20131214","journal-title":"Proceedings of the European conference on speech communication and technology"},{"key":"15_CR20","unstructured":"Villalba J, Lleida E (2010) Speaker verification performance degradation against spoofing and tampering attacks. In: FALA 10 workshop, pp 131\u2013134"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Wang ZF, Wei G, He QH (2011) Channel pattern noise based playback attack detection algorithm for speaker recognition. In: 2011 International conference on machine learning and cybernetics, vol 4, pp 1708\u20131713","DOI":"10.1109\/ICMLC.2011.6016982"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Villalba J, Lleida E (2011) Preventing replay attacks on speaker verification systems. In: 2011 IEEE International Carnahan Conference on Security Technology (ICCST). IEEE, pp 1\u20138","DOI":"10.1109\/CCST.2011.6095943"},{"key":"15_CR23","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.specom.2014.12.003","volume":"67","author":"J Ga\u0142ka","year":"2015","unstructured":"Ga\u0142ka J, Grzywacz M, Samborski R (2015) Playback attack detection for text-dependent speaker verification over telephone channels. Speech Commun 67:143\u2013153","journal-title":"Speech Commun"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Taylor P (2009) Text-to-speech synthesis. Cambridge University Press","DOI":"10.1017\/CBO9780511816338"},{"key":"15_CR25","doi-asserted-by":"crossref","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":"15_CR26","doi-asserted-by":"crossref","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":"15_CR27","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 ICASSP, pp 373\u2013376","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"15_CR28","unstructured":"Breen A, Jackson P (1998) A phonologically motivated method of selecting nonuniform units. In: Proceedings of ICSLP, pp 2735\u20132738"},{"key":"15_CR29","unstructured":"Donovan RE, Eide EM (1998) The IBM trainable speech synthesis system. In: Proceedings of ICSLP, pp 1703\u20131706"},{"issue":"2","key":"15_CR30","doi-asserted-by":"crossref","first-page":"1030","DOI":"10.1121\/1.424924","volume":"105","author":"Mark C. Beutnagel","year":"1999","unstructured":"Beutnagel B, Conkie A, Schroeter J, Stylianou Y, Syrdal A (1999) The AT&T Next-Gen TTS system. In: Proceedigns of joint ASA, EAA and DAEA meeting, pp 15\u201319","journal-title":"The Journal of the Acoustical Society of America"},{"key":"15_CR31","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 ICSLP, pp 395\u2013398","DOI":"10.21437\/ICSLP.2000-291"},{"key":"15_CR32","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, pp 2347\u20132350","DOI":"10.21437\/Eurospeech.1999-513"},{"key":"15_CR33","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":"15_CR34","doi-asserted-by":"crossref","unstructured":"Black A (2006) CLUSTERGEN: a statistical parametric synthesizer using trajectory modeling. In: Proceedings of Interspeech, pp 1762\u20131765","DOI":"10.21437\/Interspeech.2006-488"},{"issue":"1","key":"15_CR35","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1093\/ietisy\/e90-1.1.325","volume":"E90-D","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-D(1):325\u2013333","journal-title":"IEICE Transactions on Information and Systems"},{"issue":"11","key":"15_CR36","doi-asserted-by":"crossref","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 Commun 51(11):1039\u20131064","journal-title":"Speech Commun"},{"issue":"1","key":"15_CR37","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1109\/TASL.2008.2006647","volume":"17","author":"Junichi 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 (2009)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"15_CR38","doi-asserted-by":"crossref","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":"15_CR39","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":"15_CR40","doi-asserted-by":"crossref","unstructured":"Ze H, Senior A, Schuster M (2013) Statistical parametric speech synthesis using deep neural networks. In: Proceedings of ICASSP, pp 7962\u20137966","DOI":"10.1109\/ICASSP.2013.6639215"},{"issue":"10","key":"15_CR41","doi-asserted-by":"crossref","first-page":"2129","DOI":"10.1109\/TASL.2013.2269291","volume":"21","author":"ZH Ling","year":"2013","unstructured":"Ling ZH, Deng L, Yu D (2013) Modeling spectral envelopes using restricted boltzmann machines and deep belief networks for statistical parametric speech synthesis. IEEE Trans Audio Speech Lang Process 21(10):2129\u20132139","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Fan Y, Qian Y, Xie FL, Soong F (2014) TTS synthesis with bidirectional LSTM based recurrent neural networks. In: Proceedings of Interspeech, pp 1964\u20131968","DOI":"10.21437\/Interspeech.2014-443"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Zen H, Sak H (2015) Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis. In: Proceedings of ICASSP, pp 4470\u20134474","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Wu Z, King S (2016) Investigating gated recurrent networks for speech synthesis. In: Proceedings of ICASSP, pp 5140\u20135144 (2016)","DOI":"10.1109\/ICASSP.2016.7472657"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Wang X, Takaki S, Yamagishi J (2016) Investigating very deep highway networks for parametric speech synthesis. In: 9th ISCA speech synthesis workshop, pp 166\u2013171","DOI":"10.21437\/SSW.2016-27"},{"key":"15_CR46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2017.11.002","volume":"96","author":"X Wang","year":"2018","unstructured":"Wang X, Takaki S, Yamagishi J (2018) Investigating very deep highway networks for parametric speech synthesis. Speech Commun 96:1\u20139","journal-title":"Speech Commun"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Wang X, Takaki S, Yamagishi J (2017) An autoregressive recurrent mixture density network for parametric speech synthesis. In: Proceedings of ICASSP, pp 4895\u20134899","DOI":"10.1109\/ICASSP.2017.7953087"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Wang X, Takaki S, Yamagishi J (2017) An RNN-based quantized F0 model with multi-tier feedback links for text-to-speech synthesis. In: Proceedings of Interspeech, pp 1059\u20131063 (2017)","DOI":"10.21437\/Interspeech.2017-246"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Saito, Y., Takamichi, S., Saruwatari, H.: Training algorithm to deceive anti-spoofing verification for DNN-based speech synthesis. In: Proc. ICASSP, pp 4900\u20134904 (2017)","DOI":"10.1109\/ICASSP.2017.7953088"},{"issue":"1","key":"15_CR50","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/TASLP.2017.2761547","volume":"26","author":"Y Saito","year":"2018","unstructured":"Saito Y, Takamichi S, Saruwatari H (2018) Statistical parametric speech synthesis incorporating generative adversarial networks. IEEE\/ACM Trans Audio Speech Lang Process 26(1):84\u201396","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Kaneko T, Kameoka H, Hojo N, Ijima Y, Hiramatsu K, Kashino K (2017) Generative adversarial network-based postfilter for statistical parametric speech synthesis. In: Proceedings of ICASSP, pp 4910\u20134914","DOI":"10.1109\/ICASSP.2017.7953090"},{"key":"15_CR52","unstructured":"Van Oord D, Dieleman A, Zen S, Simonyan H, Vinyals K, Graves O, Kalchbrenner A, Senior N, Kavukcuoglu AK (2016) Wavenet: a generative model for raw audio. arXiv:1609.03499"},{"key":"15_CR53","unstructured":"Mehri S, Kumar K, Gulrajani I, Kumar R, Jain S, Sotelo J, Courville A, Bengio Y (2016) Samplernn: an unconditional end-to-end neural audio generation model. arXiv:1612.07837"},{"key":"15_CR54","doi-asserted-by":"crossref","unstructured":"Wang Y, Skerry-Ryan R, Stanton D, Wu Y, Weiss R, Jaitly N, Yang Z, Xiao Y, Chen Z, Bengio S, Le Q, Agiomyrgiannakis Y, Clark R, Saurous R (2017) Tacotron: towards end-to-end speech synthesis. In: Proceedings of Interspeech, pp 4006\u20134010","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"15_CR55","unstructured":"Gibiansky A, Arik S, Diamos G, Miller J, Peng K, Ping W, Raiman J, Zhou Y (2017) Deep voice 2: multi-speaker neural text-to-speech. In: Advances in neural information processing systems, pp 2966\u20132974"},{"key":"15_CR56","doi-asserted-by":"crossref","unstructured":"Shen J, Schuster M, Jaitly N, Skerry-Ryan R, Saurous R, Weiss R, Pang R, Agiomyrgiannakis Y, Wu Y, Zhang Y, Wang Y, Chen Z, Yang Z (2018) Natural tts synthesis by conditioning wavenet on mel spectrogram predictions. In: Proceedigns of ICASSP","DOI":"10.1109\/ICASSP.2018.8461368"},{"issue":"1","key":"15_CR57","doi-asserted-by":"crossref","first-page":"006","DOI":"10.3989\/loquens.2014.006","volume":"1","author":"S King","year":"2014","unstructured":"King S (2014) Measuring a decade of progress in text-to-speech. Loquens 1(1):006","journal-title":"Loquens"},{"key":"15_CR58","doi-asserted-by":"crossref","unstructured":"King S, Wihlborg L, Guo W (2017) The blizzard challenge 2017. In: Proceedings of Blizzard Challenge Workshop, Stockholm, Sweden","DOI":"10.21437\/Blizzard.2017-1"},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Foomany F, Hirschfield A, Ingleby M (2009) Toward a dynamic framework for security evaluation of voice verification systems. In: 2009 IEEE toronto international conference science and technology for humanity (TIC-STH), pp 22\u201327","DOI":"10.1109\/TIC-STH.2009.5444499"},{"key":"15_CR60","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","DOI":"10.21437\/Eurospeech.1999-286"},{"issue":"1\u20132","key":"15_CR61","doi-asserted-by":"crossref","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":"15_CR62","doi-asserted-by":"crossref","unstructured":"Masuko T, Tokuda K, Kobayashi T, Imai S (1996) Speech synthesis using HMMs with dynamic features. In: Proceedings of ICASSP","DOI":"10.1109\/ICASSP.1996.541114"},{"key":"15_CR63","doi-asserted-by":"crossref","unstructured":"Masuko T, Tokuda K, Kobayashi T, Imai S (1997) Voice characteristics conversion for HMM-based speech synthesis system. In: Proceedings of ICASSP","DOI":"10.1109\/ICASSP.1997.598807"},{"issue":"8","key":"15_CR64","doi-asserted-by":"crossref","first-page":"2280","DOI":"10.1109\/TASL.2012.2201472","volume":"20","author":"PL Leon De","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","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"15_CR65","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":"15_CR66","unstructured":"Cai W, Doshi A, Valle R (2018) Attacking speaker recognition with deep generative models. arXiv:1801.02384"},{"key":"15_CR67","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 (2001)","DOI":"10.21437\/Eurospeech.2001-239"},{"key":"15_CR68","doi-asserted-by":"crossref","unstructured":"Chen LW, Guo W, Dai LR (2010) Speaker verification against synthetic speech. In: 2010 7th International symposium on Chinese spoken language processing (ISCSLP), pp 309\u2013312","DOI":"10.1109\/ISCSLP.2010.5684887"},{"key":"15_CR69","unstructured":"Quatieri TF (2002) Discrete-time speech signal processing: principles and practice. Prentice-Hall, Inc"},{"key":"15_CR70","doi-asserted-by":"crossref","unstructured":"Wu Z, Chng E, Li H (2012) Detecting converted speech and natural speech for anti-spoofing attack in speaker recognition. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2012-465"},{"issue":"1","key":"15_CR71","doi-asserted-by":"crossref","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 Fund Electron Commun Comput Sci 88(1):280\u2013286","journal-title":"IEICE Trans Fund Electron Commun Comput Sci"},{"key":"15_CR72","doi-asserted-by":"crossref","unstructured":"De\u00a0Leon P, Stewart B, Yamagishi J (2012) Synthetic speech discrimination using pitch pattern statistics derived from image analysis. In: Proceedings of Interspeech 2012. Portland, Oregon, USA","DOI":"10.21437\/Interspeech.2012-135"},{"key":"15_CR73","doi-asserted-by":"crossref","unstructured":"Stylianou Y (2009) Voice transformation: a survey. In: Proceedings of ICASSP, pp 3585\u20133588","DOI":"10.1109\/ICASSP.2009.4960401"},{"key":"15_CR74","doi-asserted-by":"crossref","unstructured":"Pellom B, Hansen J (1999) An experimental study of speaker verification sensitivity to computer voice-altered imposters. In: Proceedings of ICASSP, vol 2, pp 837\u2013840","DOI":"10.1109\/ICASSP.1999.759801"},{"key":"15_CR75","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.specom.2017.01.008","volume":"88","author":"S Mohammadi","year":"2017","unstructured":"Mohammadi S, Kain A (2017) An overview of voice conversion systems. Speech Commun 88:65\u201382","journal-title":"Speech Commun"},{"key":"15_CR76","doi-asserted-by":"crossref","unstructured":"Abe M, Nakamura S, Shikano K, Kuwabara H (1988) Voice conversion through vector quantization. In: Proceedigns of ICASSP, pp 655\u2013658","DOI":"10.1109\/ICASSP.1988.196671"},{"issue":"3","key":"15_CR77","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/S0167-6393(99)00015-1","volume":"28","author":"L Arslan","year":"1999","unstructured":"Arslan L (1999) Speaker transformation algorithm using segmental codebooks (STASC). Speech Commun 28(3):211\u2013226","journal-title":"Speech Commun"},{"key":"15_CR78","doi-asserted-by":"crossref","unstructured":"Kain A, Macon M (1998) Spectral voice conversion for text-to-speech synthesis. In: Proceedings of ICASSP vol 1, pp 285\u2013288","DOI":"10.1109\/ICASSP.1998.674423"},{"issue":"2","key":"15_CR79","doi-asserted-by":"crossref","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":"15_CR80","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","volume":"15","author":"T Toda","year":"2007","unstructured":"Toda T, Black A, 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":"15_CR81","doi-asserted-by":"crossref","unstructured":"Kobayashi K, Toda T, Neubig G, Sakti S, Nakamura S (2014) Statistical singing voice conversion with direct waveform modification based on the spectrum differential. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2014-539"},{"key":"15_CR82","doi-asserted-by":"crossref","unstructured":"Popa V, Silen H, Nurminen J, Gabbouj M (2012) Local linear transformation for voice conversion. In: Proceedigns of ICASSP. IEEE, pp 4517\u20134520","DOI":"10.1109\/ICASSP.2012.6288922"},{"key":"15_CR83","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, pp 2413\u20132416","DOI":"10.21437\/Eurospeech.2003-664"},{"key":"15_CR84","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: Proceedigns of Interspeech","DOI":"10.1109\/ISCSLP.2012.6423477"},{"issue":"5","key":"15_CR85","doi-asserted-by":"crossref","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":"15_CR86","doi-asserted-by":"crossref","unstructured":"Pilkington N, Zen H, Gales M (2011) Gaussian process experts for voice conversion. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2011-691"},{"key":"15_CR87","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, pp 653\u2013656","DOI":"10.21437\/Interspeech.2011-268"},{"issue":"2","key":"15_CR88","doi-asserted-by":"crossref","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":"15_CR89","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1109\/LSP.2012.2225615","volume":"19","author":"Zhizheng Wu","year":"2012","unstructured":"Wu Z, Kinnunen T, Chng E, Li H (2012) Mixture of factor analyzers using priors from non-parallel speech for voice conversion. IEEE Signal Process Lett 19(12)","journal-title":"IEEE Signal Processing Letters"},{"issue":"6","key":"15_CR90","doi-asserted-by":"crossref","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":"18","key":"15_CR91","doi-asserted-by":"crossref","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":"15_CR92","doi-asserted-by":"crossref","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 Transactions on Audio, Speech, and Language Processing"},{"key":"15_CR93","doi-asserted-by":"crossref","unstructured":"Wu Z, Chng E, 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). IEEE","DOI":"10.1109\/ChinaSIP.2013.6625307"},{"issue":"2","key":"15_CR94","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/0167-6393(94)00058-I","volume":"16","author":"M Narendranath","year":"1995","unstructured":"Narendranath M, Murthy H, 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":"15_CR95","doi-asserted-by":"crossref","unstructured":"Desai S, Raghavendra E, Yegnanarayana B, Black A, Prahallad K (2009) Voice conversion using artificial neural networks. In: Proceedings of ICASSP. IEEE, pp 3893\u20133896","DOI":"10.1109\/ICASSP.2009.4960478"},{"issue":"8","key":"15_CR96","doi-asserted-by":"crossref","first-page":"1925","DOI":"10.1587\/transinf.2017EDL8034","volume":"E100.D","author":"Yuki SAITO","year":"2017","unstructured":"Saito Y, Takamichi S, Saruwatari H (2017) Voice conversion using input-to-output highway networks. IEICE Transactions on Inf Syst E100.D(8):1925\u20131928","journal-title":"IEICE Transactions on Information and Systems"},{"issue":"3","key":"15_CR97","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1109\/TASLP.2014.2379589","volume":"23","author":"Toru Nakashika","year":"2015","unstructured":"Nakashika T, Takiguchi T, Ariki Y (2015) Voice conversion using RNN pre-trained by recurrent temporal restricted boltzmann machines. IEEE\/ACM Trans Audio Speech Lang Process (TASLP) 23(3):580\u2013587","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"15_CR98","doi-asserted-by":"crossref","unstructured":"Sun L, Kang S, Li K, Meng H (2015) Voice conversion using deep bidirectional long short-term memory based recurrent neural networks. In: Proceedings of ICASSP, pp 4869\u20134873","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"15_CR99","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. IEEE"},{"issue":"5","key":"15_CR100","doi-asserted-by":"crossref","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":"15_CR101","doi-asserted-by":"crossref","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":"15_CR102","doi-asserted-by":"crossref","unstructured":"Hsu CC, Hwang HT, Wu YC, Tsao Y, Wang HM (2017) Voice conversion from unaligned corpora using variational autoencoding wasserstein generative adversarial networks. In: Proceedings of Interspeech, vol 2017, pp 3364\u20133368","DOI":"10.21437\/Interspeech.2017-63"},{"key":"15_CR103","doi-asserted-by":"crossref","unstructured":"Miyoshi H, Saito Y, Takamichi S, Saruwatari H (2017) Voice conversion using sequence-to-sequence learning of context posterior probabilities. Proceedings of Interspeech, vol 2017, pp 1268\u20131272","DOI":"10.21437\/Interspeech.2017-247"},{"key":"15_CR104","doi-asserted-by":"crossref","unstructured":"Fang F, Yamagishi J, Echizen I, Lorenzo-Trueba J (2018) High-quality nonparallel voice conversion based on cycle-consistent adversarial network. In: Proceedings of ICASSP 2018","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"15_CR105","doi-asserted-by":"crossref","unstructured":"Kobayashi K, Hayashi T, Tamamori A, Toda T (2017) Statistical voice conversion with wavenet-based waveform generation. In: Proceedings of Interspeech, pp 1138\u20131142","DOI":"10.21437\/Interspeech.2017-986"},{"key":"15_CR106","doi-asserted-by":"crossref","unstructured":"Gillet B, King S (2003) Transforming F0 contours. In: Proceedings of EUROSPEECH, pp 101\u2013104 (2003)","DOI":"10.21437\/Eurospeech.2003-74"},{"issue":"4","key":"15_CR107","doi-asserted-by":"crossref","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":"15_CR108","doi-asserted-by":"crossref","unstructured":"Helander E, Nurminen J (2007) A novel method for prosody prediction in voice conversion. In: Proceedings of ICASSP, vol\u00a04. IEEE, pp IV\u2013509","DOI":"10.1109\/ICASSP.2007.366961"},{"key":"15_CR109","doi-asserted-by":"crossref","unstructured":"Wu Z, Kinnunen T, Chng E, Li H (2010) Text-independent F0 transformation with non-parallel data for voice conversion. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2010-497"},{"key":"15_CR110","first-page":"111","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":"15_CR111","doi-asserted-by":"crossref","unstructured":"Toda T, Chen LH, Saito D, Villavicencio F, Wester M, Wu Z, Yamagishi J (2016) The voice conversion challenge 2016. In: Proceedings of Interspeech, pp 1632\u20131636","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"15_CR112","doi-asserted-by":"crossref","unstructured":"Wester M, Wu Z, Yamagishi J (2016) Analysis of the voice conversion challenge 2016 evaluation results. In: Proceedings of Interspeech, pp 1637\u20131641","DOI":"10.21437\/Interspeech.2016-1331"},{"key":"15_CR113","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 ICASSP, vol\u00a01. IEEE, pp 17\u201320","DOI":"10.1109\/ICASSP.2005.1415039"},{"key":"15_CR114","doi-asserted-by":"crossref","unstructured":"Matrouf D, Bonastre JF, Fredouille C (2006) Effect of speech transformation on impostor acceptance. In: Proceedings of ICASSP, vol\u00a01. IEEE, pp I\u2013I","DOI":"10.1109\/ICASSP.2006.1660175"},{"key":"15_CR115","doi-asserted-by":"crossref","unstructured":"Kinnunen T, Wu Z, Lee K, Sedlak F, Chng E, Li H (2012) Vulnerability of speaker verification systems against voice conversion spoofing attacks: the case of telephone speech. In: Proceedings of ICASSP. IEEE, pp 4401\u20134404","DOI":"10.1109\/ICASSP.2012.6288895"},{"key":"15_CR116","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 ICASSP, vol\u00a01, pp I\u2013I","DOI":"10.1109\/ICASSP.2006.1659962"},{"key":"15_CR117","doi-asserted-by":"crossref","unstructured":"Wu Z, Larcher A, Lee K, Chng E, Kinnunen T, Li H (2013) Vulnerability evaluation of speaker verification under voice conversion spoofing: the effect of text constraints. In: Proceedings of Interspeech, Lyon, France (2013)","DOI":"10.21437\/Interspeech.2013-293"},{"key":"15_CR118","unstructured":"Alegre F, Vipperla R, Evans N, Fauve B (2012) On the vulnerability of automatic speaker recognition to spoofing attacks with artificial signals. In: 2012 EURASIP conference on european conference on signal processing (EUSIPCO)"},{"key":"15_CR119","doi-asserted-by":"crossref","unstructured":"De\u00a0Leon PL, Hernaez I, Saratxaga I, Pucher M, Yamagishi J (2011) Detection of synthetic speech for the problem of imposture. In: Proceedings of ICASSP, Dallas, USA, pp 4844\u20134847","DOI":"10.1109\/ICASSP.2011.5947440"},{"key":"15_CR120","unstructured":"Wu Z, Kinnunen T, Chng E, Li H, Ambikairajah E (2012) A study on spoofing attack in state-of-the-art speaker verification: the telephone speech case. In: Proceedings of Asia-Pacific signal information processing association annual summit and conference (APSIPA ASC). IEEE, pp 1\u20135"},{"key":"15_CR121","doi-asserted-by":"crossref","unstructured":"Alegre F, Vipperla R, Evans,N (2012) Spoofing countermeasures for the protection of automatic speaker recognition systems against attacks with artificial signals. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2012-462"},{"key":"15_CR122","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 ICASSP","DOI":"10.1109\/ICASSP.2013.6638222"},{"key":"15_CR123","doi-asserted-by":"crossref","unstructured":"Wu Z, Xiao X, Chng E, Li H (2013) Synthetic speech detection using temporal modulation feature. In: Proceedings of ICASSP","DOI":"10.1109\/ICASSP.2013.6639067"},{"key":"15_CR124","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, Lyon, France","DOI":"10.21437\/Interspeech.2013-291"},{"key":"15_CR125","doi-asserted-by":"crossref","unstructured":"Wu Z, Kinnunen T, Evans N, Yamagishi J, Hanil\u00e7i C, Sahidullah M, Sizov A (2015) ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures challenge. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2015-462"},{"key":"15_CR126","doi-asserted-by":"crossref","unstructured":"Kinnunen T, Sahidullah M, Delgado H, Todisco M, Evans N, Yamagishi J, Lee K (2017) The ASVspoof 2017 challenge: assessing the limits of replay spoofing attack detection. In: INTERSPEECH","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"15_CR127","doi-asserted-by":"crossref","unstructured":"Wu Z, Khodabakhsh A, Demiroglu C, Yamagishi J, Saito D, Toda T, King S (2015) SAS: a speaker verification spoofing database containing diverse attacks. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","DOI":"10.1109\/ICASSP.2015.7178810"},{"key":"15_CR128","doi-asserted-by":"crossref","unstructured":"Wu Z, Kinnunen T, Evans N, Yamagishi J (2014) ASVspoof 2015: automatic speaker verification spoofing and countermeasures challenge evaluation plan. http:\/\/www.spoofingchallenge.org\/asvSpoof.pdf","DOI":"10.21437\/Interspeech.2015-462"},{"key":"15_CR129","doi-asserted-by":"crossref","unstructured":"Patel T, Patil H (2015) Combining evidences from mel cepstral, cochlear filter cepstral and instantaneous frequency features for detection of natural vs. spoofed speech. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2015-467"},{"key":"15_CR130","doi-asserted-by":"crossref","unstructured":"Novoselov S, Kozlov A, Lavrentyeva G, Simonchik K, Shchemelinin V (2016) STC anti-spoofing systems for the ASVspoof 2015 challenge. In: Proceedings of IEEE international conference on acoustics, speech, and signal processing (ICASSP), pp 5475\u20135479","DOI":"10.1109\/ICASSP.2016.7472724"},{"key":"15_CR131","doi-asserted-by":"crossref","unstructured":"Chen N, Qian Y, Dinkel H, Chen B, Yu K (2015) Robust deep feature for spoofing detection-the SJTU system for ASVspoof 2015 challenge. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2015-474"},{"key":"15_CR132","doi-asserted-by":"crossref","unstructured":"Xiao X, Tian X, Du S, Xu H, Chng E, Li H (2015) Spoofing speech detection using high dimensional magnitude and phase features: the NTU approach for ASVspoof 2015 challenge. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2015-465"},{"key":"15_CR133","doi-asserted-by":"crossref","unstructured":"Alam M, Kenny P, Bhattacharya G, Stafylakis T (2015) Development of CRIM system for the automatic speaker verification spoofing and countermeasures challenge 2015. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2015-469"},{"issue":"4","key":"15_CR134","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1109\/JSTSP.2017.2671435","volume":"11","author":"Z Wu","year":"2017","unstructured":"Wu Z, Yamagishi J, Kinnunen T, Hanil\u00e7i C, Sahidullah M, Sizov A, Evans N, Todisco M, Delgado H (2017) Asvspoof: the automatic speaker verification spoofing and countermeasures challenge. IEEE J Sel Top Signal Process 11(4):588\u2013604","journal-title":"IEEE J Sel Top Signal Process"},{"key":"15_CR135","doi-asserted-by":"crossref","unstructured":"Delgado H, Todisco M, Sahidullah M, Evans N, Kinnunen T, Lee K, Yamagishi J (2018) ASVspoof 2017 version 2.0: meta-data analysis and baseline enhancements. In: Proceedings of Odyssey 2018 the speaker and language recognition workshop, pp 296\u2013303","DOI":"10.21437\/Odyssey.2018-42"},{"key":"15_CR136","doi-asserted-by":"crossref","unstructured":"Todisco M, Delgado H, Evans N (2016) A new feature for automatic speaker verification anti-spoofing: constant Q cepstral coefficients. In: Proceedings of Odyssey: the speaker and language recognition workshop, Bilbao, Spain, pp 283\u2013290","DOI":"10.21437\/Odyssey.2016-41"},{"key":"15_CR137","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1016\/j.csl.2017.01.001","volume":"45","author":"M Todisco","year":"2017","unstructured":"Todisco M, Delgado H, Evans N (2017) Constant Q cepstral coefficients: a spoofing countermeasure for automatic speaker verification. Comput Speech Lang 45:516\u2013535","journal-title":"Comput Speech Lang"},{"key":"15_CR138","doi-asserted-by":"crossref","unstructured":"Lavrentyeva G, Novoselov S, Malykh E, Kozlov A, Kudashev O, Shchemelinin V (2017) Audio replay attack detection with deep learning frameworks. In: Proceedings of Interspeech, pp 82\u201386","DOI":"10.21437\/Interspeech.2017-360"},{"key":"15_CR139","doi-asserted-by":"crossref","unstructured":"Ji Z, Li Z, Li P, An M, Gao S, Wu D, Zhao F (2017) Ensemble learning for countermeasure of audio replay spoofing attack in ASVspoof2017. In: Proceedings of Interspeech, pp 87\u201391","DOI":"10.21437\/Interspeech.2017-1246"},{"key":"15_CR140","doi-asserted-by":"crossref","unstructured":"Li L, Chen Y, Wang D, Zheng T (2017) A study on replay attack and anti-spoofing for automatic speaker verification. In: Proceedings of Interspeech, pp 92\u201396","DOI":"10.21437\/Interspeech.2017-456"},{"key":"15_CR141","doi-asserted-by":"crossref","unstructured":"Patil H, Kamble M, Patel T, Soni M (2017) Novel variable length teager energy separation based instantaneous frequency features for replay detection. In: Proceedings of Interspeech, pp 12\u201316","DOI":"10.21437\/Interspeech.2017-1362"},{"key":"15_CR142","doi-asserted-by":"crossref","unstructured":"Chen Z, Xie Z, Zhang W, Xu X (2017) ResNet and model fusion for automatic spoofing detection. In: Proceedings of Interspeech, pp 102\u2013106","DOI":"10.21437\/Interspeech.2017-1085"},{"key":"15_CR143","doi-asserted-by":"crossref","unstructured":"Wu Z, Gao S, Cling E, Li H (2014) A study on replay attack and anti-spoofing for text-dependent speaker verification. In: Proceedings of Asia-Pacific signal information processing association annual summit and conference (APSIPA ASC). IEEE, pp 1\u20135","DOI":"10.1109\/APSIPA.2014.7041636"},{"key":"15_CR144","doi-asserted-by":"crossref","unstructured":"Li Q (2009) An auditory-based transform for audio signal processing. In: 2009 IEEE workshop on applications of signal processing to audio and acoustics. IEEE, pp 181\u2013184","DOI":"10.1109\/ASPAA.2009.5346541"},{"issue":"4","key":"15_CR145","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis S, Mermelstein P (1980) Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans Acoust Speech Signal Process 28(4):357\u2013366","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"15_CR146","doi-asserted-by":"crossref","unstructured":"Sahidullah M, Kinnunen T, Hanil\u00e7i C (2015) A comparison of features for synthetic speech detection. In: Proceedings of Interspeech. ISCA, pp 2087\u20132091","DOI":"10.21437\/Interspeech.2015-472"},{"issue":"1","key":"15_CR147","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1121\/1.400476","volume":"89","author":"J Brown","year":"1991","unstructured":"Brown J (1991) Calculation of a constant Q spectral transform. J Acoust Soc Am 89(1):425\u2013434","journal-title":"J Acoust Soc Am"},{"key":"15_CR148","doi-asserted-by":"crossref","unstructured":"Alam M, Kenny P (2017) Spoofing detection employing infinite impulse response\u2014constant Q transform-based feature representations. In: Proceedings of European signal processing conference (EUSIPCO)","DOI":"10.23919\/EUSIPCO.2017.8081177"},{"key":"15_CR149","unstructured":"Cancela P, Rocamora M, L\u00f3pez E (2009) An efficient multi-resolution spectral transform for music analysis. In: Proceedings of international society for music information retrieval conference, pp 309\u2013314"},{"issue":"1","key":"15_CR150","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000006","volume":"2","author":"Y Bengio","year":"2009","unstructured":"Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2(1):1\u2013127","journal-title":"Found Trends Mach Learn"},{"volume-title":"Deep learning","year":"2016","author":"I Goodfellow","key":"15_CR151","unstructured":"Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning. MIT Press, Cambridge"},{"key":"15_CR152","doi-asserted-by":"crossref","unstructured":"Tian Y, Cai M, He L, Liu J (2015) Investigation of bottleneck features and multilingual deep neural networks for speaker verification. In: Proceedings of Interspeech, pp 1151\u20131155","DOI":"10.21437\/Interspeech.2015-300"},{"issue":"10","key":"15_CR153","doi-asserted-by":"crossref","first-page":"1671","DOI":"10.1109\/LSP.2015.2420092","volume":"22","author":"F Richardson","year":"2015","unstructured":"Richardson F, Reynolds D, Dehak N (2015) Deep neural network approaches to speaker and language recognition. IEEE Signal Process Lett 22(10):1671\u20131675","journal-title":"IEEE Signal Process Lett"},{"issue":"6","key":"15_CR154","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"Geoffrey Hinton","year":"2012","unstructured":"Hinton G, Deng L, Yu D, Dahl GE, Mohamed RA, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath TN, Kingsbury B (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag 29(6):82\u201397","journal-title":"IEEE Signal Processing Magazine"},{"key":"15_CR155","doi-asserted-by":"crossref","unstructured":"Alam M, Kenny P, Gupta V, Stafylakis T (2016) Spoofing detection on the ASVspoof2015 challenge corpus employing deep neural networks. In: Proceedings of Odyssey: the Speaker and Language Recognition Workshop, Bilbao, Spain, pp 270\u2013276","DOI":"10.21437\/Odyssey.2016-39"},{"key":"15_CR156","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.specom.2016.10.007","volume":"85","author":"Y Qian","year":"2016","unstructured":"Qian Y, Chen N, Yu K (2016) Deep features for automatic spoofing detection. Speech Commun 85:43\u201352","journal-title":"Speech Commun"},{"key":"15_CR157","doi-asserted-by":"crossref","first-page":"4779","DOI":"10.1109\/ACCESS.2017.2687041","volume":"5","author":"H Yu","year":"2017","unstructured":"Yu H, Tan ZH, Zhang Y, Ma Z, Guo J (2017) DNN filter bank cepstral coefficients for spoofing detection. IEEE Access 5:4779\u20134787","journal-title":"IEEE Access"},{"issue":"4","key":"15_CR158","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1109\/JSTSP.2016.2647202","volume":"11","author":"K Sriskandaraja","year":"2017","unstructured":"Sriskandaraja K, Sethu V, Ambikairajah E, Li H (2017) Front-end for antispoofing countermeasures in speaker verification: scattering spectral decomposition. IEEE J Sel Top Signal Process 11(4):632\u2013643. https:\/\/doi.org\/10.1109\/JSTSP.2016.2647202","journal-title":"IEEE J Sel Top Signal Process"},{"issue":"16","key":"15_CR159","doi-asserted-by":"crossref","first-page":"4114","DOI":"10.1109\/TSP.2014.2326991","volume":"62","author":"J And\u00e9n","year":"2014","unstructured":"And\u00e9n J, Mallat S (2014) Deep scattering spectrum. IEEE Trans Signal Process 62(16):4114\u20134128","journal-title":"IEEE Trans Signal Process"},{"key":"15_CR160","doi-asserted-by":"crossref","first-page":"1331","DOI":"10.1002\/cpa.21413","volume":"65","author":"S Mallat","year":"2012","unstructured":"Mallat S (2012) Group invariant scattering. Commun Pure Appl Math 65:1331\u20131398","journal-title":"Commun Pure Appl Math"},{"key":"15_CR161","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.csl.2017.10.001","volume":"48","author":"M Pal","year":"2018","unstructured":"Pal M, Paul D, Saha G (2018) Synthetic speech detection using fundamental frequency variation and spectral features. Comput Speech Lang 48:31\u201350","journal-title":"Comput Speech Lang"},{"key":"15_CR162","first-page":"29","volume":"2008","author":"K Laskowski","year":"2008","unstructured":"Laskowski K, Heldner M, Edlund J (2008) The fundamental frequency variation spectrum. Proc FONETIK 2008:29\u201332","journal-title":"Proc FONETIK"},{"key":"15_CR163","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.specom.2016.04.001","volume":"81","author":"I Saratxaga","year":"2016","unstructured":"Saratxaga I, Sanchez J, Wu Z, Hernaez I, Navas E (2016) Synthetic speech detection using phase information. Speech Commun 81:30\u201341","journal-title":"Speech Commun"},{"issue":"4","key":"15_CR164","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1109\/JSTSP.2017.2694139","volume":"11","author":"L Wang","year":"2017","unstructured":"Wang L, Nakagawa S, Zhang Z, Yoshida Y, Kawakami Y (2017) Spoofing speech detection using modified relative phase information. IEEE J Sel Top Signal Process 11(4):660\u2013670","journal-title":"IEEE J Sel Top Signal Process"},{"issue":"1","key":"15_CR165","first-page":"11","volume":"5","author":"S Chakroborty","year":"2009","unstructured":"Chakroborty S, Saha G (2009) Improved text-independent speaker identification using fused MFCC & IMFCC feature sets based on Gaussian filter. Int J Signal Process 5(1):11\u201319","journal-title":"Int J Signal Process"},{"issue":"11","key":"15_CR166","doi-asserted-by":"crossref","first-page":"2884","DOI":"10.1109\/TIFS.2018.2833032","volume":"13","author":"X Wu","year":"2018","unstructured":"Wu X, He R, Sun Z, Tan T (2018) A light CNN for deep face representation with noisy labels. IEEE Trans Inf Forensics Secur 13(11):2884\u20132896","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"15_CR167","doi-asserted-by":"publisher","unstructured":"Goncalves AR, Violato RPV, Korshunov P, Marcel S, Simoes FO (2017) On the generalization of fused systems in voice presentation attack detection. In: 2017 International conference of the biometrics special interest group (BIOSIG), pp 1\u20135. https:\/\/doi.org\/10.23919\/BIOSIG.2017.8053516","DOI":"10.23919\/BIOSIG.2017.8053516"},{"key":"15_CR168","doi-asserted-by":"crossref","unstructured":"Paul D, Pal M, Saha G (2016) Novel speech features for improved detection of spoofing attacks. In: Proceedings of annual IEEE India conference (INDICON)","DOI":"10.1109\/INDICON.2015.7443805"},{"issue":"4","key":"15_CR169","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"Najim 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 Transactions on Audio, Speech, and Language Processing"},{"key":"15_CR170","doi-asserted-by":"crossref","unstructured":"Khoury E, Kinnunen T, Sizov A, Wu Z, Marcel S (2014) Introducing i-vectors for joint anti-spoofing and speaker verification. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2014-13"},{"issue":"4","key":"15_CR171","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1109\/TIFS.2015.2407362","volume":"10","author":"A Sizov","year":"2015","unstructured":"Sizov A, Khoury E, Kinnunen T, Wu Z, Marcel S (2015) Joint speaker verification and antispoofing in the i-vector space. IEEE Trans Inf Forensics Secur 10(4):821\u2013832","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"15_CR172","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.dsp.2017.10.010","volume":"72","author":"C Hanil\u00e7i","year":"2018","unstructured":"Hanil\u00e7i C (2018) Data selection for i-vector based automatic speaker verification anti-spoofing. Digit Signal Process 72:171\u2013180","journal-title":"Digit Signal Process"},{"key":"15_CR173","doi-asserted-by":"crossref","unstructured":"Tian X, Wu Z, Xiao X, Chng E, Li H (2016) Spoofing detection from a feature representation perspective. In: Proceedings of IEEE international conference on acoustics, speech, and signal processing (ICASSP), pp 2119\u20132123","DOI":"10.1109\/ICASSP.2016.7472051"},{"key":"15_CR174","doi-asserted-by":"crossref","unstructured":"Yu H, Tan ZH, Ma Z, Martin R, Guo J (2018) Spoofing detection in automatic speaker verification systems using dnn classifiers and dynamic acoustic features. IEEE Trans Neural Netw Learn Syst PP(99):1\u201312","DOI":"10.1109\/TNNLS.2017.2771947"},{"key":"15_CR175","doi-asserted-by":"crossref","unstructured":"Dinkel H, Chen N, Qian Y, Yu K (2017) End-to-end spoofing detection with raw waveform cldnns. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp 4860\u20134864","DOI":"10.1109\/ICASSP.2017.7953080"},{"key":"15_CR176","doi-asserted-by":"crossref","unstructured":"Sainath T, Weiss R, Senior A, Wilson K, Vinyals O (2015) Learning the speech front-end with raw waveform CLDNNs. In: Proceedigns of Interspeech","DOI":"10.21437\/Interspeech.2015-1"},{"issue":"4","key":"15_CR177","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1109\/JSTSP.2016.2647199","volume":"11","author":"C Zhang","year":"2017","unstructured":"Zhang C, Yu C, Hansen JHL (2017) An investigation of deep-learning frameworks for speaker verification antispoofing. IEEE J Sel Top Signal Process 11(4):684\u2013694","journal-title":"IEEE J Sel Top Signal Process"},{"key":"15_CR178","doi-asserted-by":"crossref","unstructured":"Muckenhirn H, Magimai-Doss M, Marcel S (2017) End-to-end convolutional neural network-based voice presentation attack detection. In: 2017 IEEE international joint conference on biometrics (IJCB), pp 335\u2013341","DOI":"10.1109\/BTAS.2017.8272715"},{"key":"15_CR179","doi-asserted-by":"crossref","unstructured":"Chen S, Ren K, Piao S, Wang C, Wang Q, Weng J, Su L, Mohaisen A (2017) You can hear but you cannot steal: Defending against voice impersonation attacks on smartphones. In: 2017 IEEE 37th international conference on distributed computing systems (ICDCS). IEEE, pp 183\u2013195","DOI":"10.1109\/ICDCS.2017.133"},{"key":"15_CR180","doi-asserted-by":"crossref","unstructured":"Shiota S, Villavicencio F, Yamagishi J, Ono N, Echizen I, Matsui T (2015) Voice liveness detection algorithms based on pop noise caused by human breath for automatic speaker verification. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2015-92"},{"key":"15_CR181","doi-asserted-by":"crossref","unstructured":"Shiota S, Villavicencio F, Yamagishi J, Ono N, Echizen I, Matsui T (2016) Voice liveness detection for speaker verification based on a tandem single\/double-channel pop noise detector. In: ODYSSEY","DOI":"10.21437\/Odyssey.2016-37"},{"issue":"1","key":"15_CR182","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/TASLP.2017.2760243","volume":"26","author":"M Sahidullah","year":"2018","unstructured":"Sahidullah M, Thomsen D, Hautam\u00e4ki R, Kinnunen T, Tan ZH, Parts R, Pitk\u00e4nen M (2018) Robust voice liveness detection and speaker verification using throat microphones. IEEE\/ACM Trans Audio Speech Lang Process 26(1):44\u201356","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"15_CR183","doi-asserted-by":"crossref","unstructured":"Elko G, Meyer J, Backer S, Peissig J (2007) Electronic pop protection for microphones. In: 2007 IEEE workshop on applications of signal processing to audio and acoustics. IEEE, pp 46\u201349","DOI":"10.1109\/ASPAA.2007.4393041"},{"key":"15_CR184","doi-asserted-by":"crossref","unstructured":"Zhang L, Tan S, Yang J, Chen Y (2016) Voicelive: a phoneme localization based liveness detection for voice authentication on smartphones. In: Proceedings of the 2016 ACM SIGSAC conference on computer and communications security. ACM, pp 1080\u20131091","DOI":"10.1145\/2976749.2978296"},{"key":"15_CR185","doi-asserted-by":"crossref","unstructured":"Zhang L, Tan S, Yang J (2017) Hearing your voice is not enough: An articulatory gesture based liveness detection for voice authentication. In: Proceedings of the 2017 ACM SIGSAC conference on computer and communications security. ACM, pp 57\u201371","DOI":"10.1145\/3133956.3133962"},{"key":"15_CR186","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.specom.2016.10.002","volume":"85","author":"C Hanil\u00e7i","year":"2016","unstructured":"Hanil\u00e7i C, Kinnunen T, Sahidullah M, Sizov A (2016) Spoofing detection goes noisy: an analysis of synthetic speech detection in the presence of additive noise. Speech Commun 85:83\u201397","journal-title":"Speech Commun"},{"key":"15_CR187","doi-asserted-by":"crossref","unstructured":"Yu H, Sarkar A, Thomsen D, Tan ZH, Ma Z, Guo J (2016) Effect of multi-condition training and speech enhancement methods on spoofing detection. In: Proceedings of international workshop on sensing, processing and learning for intelligent machines (SPLINE)","DOI":"10.1109\/SPLIM.2016.7528399"},{"key":"15_CR188","doi-asserted-by":"crossref","unstructured":"Tian X, Wu Z, Xiao X, Chng E, Li H (2016) An investigation of spoofing speech detection under additive noise and reverberant conditions. In: Proceedings of Interspeech (2016)","DOI":"10.21437\/Interspeech.2016-743"},{"key":"15_CR189","doi-asserted-by":"crossref","unstructured":"Delgado H, Todisco M, Evans N, Sahidullah M, Liu W, Alegre F, Kinnunen T, Fauve B (2017) Impact of bandwidth and channel variation on presentation attack detection for speaker verification. In: 2017 International conference of the biometrics special interest group (BIOSIG), pp 1\u20136","DOI":"10.23919\/BIOSIG.2017.8053510"},{"issue":"10","key":"15_CR190","doi-asserted-by":"crossref","first-page":"1942","DOI":"10.1109\/TASLP.2017.2732162","volume":"25","author":"Y Qian","year":"2017","unstructured":"Qian Y, Chen N, Dinkel H, Wu Z (2017) Deep feature engineering for noise robust spoofing detection. IEEE\/ACM Trans Audio Speech Lang Process 25(10):1942\u20131955","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"15_CR191","doi-asserted-by":"crossref","unstructured":"Korshunov P, Marcel S (2016) Cross-database evaluation of audio-based spoofing detection systems. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2016-1326"},{"key":"15_CR192","doi-asserted-by":"crossref","unstructured":"Paul D, Sahidullah M, Saha G (2017) Generalization of spoofing countermeasures: a case study with ASVspoof 2015 and BTAS 2016 corpora. In: Proceedigns of IEEE international conference on acoustics, speech, and signal processing (ICASSP). IEEE pp 2047\u20132051","DOI":"10.1109\/ICASSP.2017.7952516"},{"key":"15_CR193","doi-asserted-by":"crossref","unstructured":"Lorenzo-Trueba J, Fang F, Wang X, Echizen I, Yamagishi J, Kinnunen T (2018) Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama\u2019s voice using GAN, WaveNet and low-quality found data. In: Proceedings of Odyssey: the speaker and language recognition workshop","DOI":"10.21437\/Odyssey.2018-34"},{"key":"15_CR194","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672\u20132680"},{"key":"15_CR195","doi-asserted-by":"crossref","unstructured":"Kreuk F, Adi Y, Cisse M, Keshet J (2018) Fooling end-to-end speaker verification by adversarial examples. arXiv:1801.03339","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"15_CR196","doi-asserted-by":"crossref","unstructured":"Sahidullah M, Delgado H, Todisco M, Yu H, Kinnunen T, Evans N, Tan ZH (2016) Integrated spoofing countermeasures and automatic speaker verification: an evaluation on ASVspoof 2015. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2016-1280"},{"issue":"11","key":"15_CR197","doi-asserted-by":"crossref","first-page":"2098","DOI":"10.1109\/TASLP.2017.2743340","volume":"25","author":"H Muckenhirn","year":"2017","unstructured":"Muckenhirn H, Korshunov P, Magimai-Doss M, Marcel S (2017) Long-term spectral statistics for voice presentation attack detection. IEEE\/ACM Trans Audio Speech Lang Process 25(11):2098\u20132111","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"15_CR198","doi-asserted-by":"crossref","unstructured":"Sarkar A, Sahidullah M, Tan ZH, Kinnunen T (2017) Improving speaker verification performance in presence of spoofing attacks using out-of-domain spoofed data. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2017-1758"},{"key":"15_CR199","doi-asserted-by":"crossref","unstructured":"Kinnunen T, Lee K, Delgado H, Evans N, Todisco M, Sahidullah M, Yamagishi J, Reynolds D (2018) t-DCF: a detection cost function for the tandem assessment of spoofing countermeasures and automatic speaker verification. In: Proceedings of Odyssey: the speaker and language recognition workshop","DOI":"10.21437\/Odyssey.2018-44"},{"key":"15_CR200","doi-asserted-by":"crossref","unstructured":"Todisco M, Delgado H, Lee K, Sahidullah M, Evans N, Kinnunen T, Yamagishi J (2018) Integrated presentation attack detection and automatic speaker verification: common features and Gaussian back-end fusion. In: Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2018-2289"},{"issue":"4","key":"15_CR201","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1109\/TASLP.2016.2526653","volume":"24","author":"Z Wu","year":"2016","unstructured":"Wu Z, De Leon P, Demiroglu C, Khodabakhsh A, King S, Ling ZH, Saito D, Stewart B, Toda T, Wester M, Yamagishi Y (2016) Anti-spoofing for text-independent speaker verification: an initial database, comparison of countermeasures, and human performance. IEEE\/ACM Trans Audio Speech Lang Process 24(4):768\u2013783","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"}],"container-title":["Advances in Computer Vision and Pattern Recognition","Handbook of Biometric Anti-Spoofing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-92627-8_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T19:04:17Z","timestamp":1720897457000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-92627-8_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783319926261","9783319926278"],"references-count":201,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-92627-8_15","relation":{},"ISSN":["2191-6586","2191-6594"],"issn-type":[{"type":"print","value":"2191-6586"},{"type":"electronic","value":"2191-6594"}],"subject":[],"published":{"date-parts":[[2019]]}}}