Evaluation of speaker verification security and detection of HMM-based synthetic speech

IEEE Transactions on Audio, Speech and Language Processing

Volumn 20, Issue 8, 2012, Pages 2280-2290

  De Leon, Phillip L ^a   Pucher, Michael ^b   Yamagishi, Junichi ^c   Hernaez, Inma ^d   Saratxaga, Ibon ^d  

^a Horeshoe Cir Jett Hall   (United States)

^b TELECOMMUNICATIONS RESEARCH CENTER VIENNA FTW   (Austria)

^c UNIVERSITY OF EDINBURGH   (United Kingdom)

^d UNIVERSITY OF THE BASQUE COUNTRY UPV EHU   (Spain)

Author keywords

Security; speaker recognition; speech synthesis

Indexed keywords

AVERAGE-VOICE; BACKGROUND MODEL; EQUAL ERROR RATE; FEATURE-BASED; GAUSSIAN MIXTURE MODEL-UNIVERSAL BACKGROUND MODELS; MODEL ADAPTATION; RELATIVE PHASE; RELIABLE DETECTION; SECURITY; SPEAKER MODEL; SPEAKER RECOGNITION; SPEAKER VERIFICATION; SPEECH CORPORA; SYNTHETIC SPEECH; TARGET SPEAKER; TEXT-TO-SPEECH SYNTHESIZERS; TRAINING DATA; WALL STREET JOURNAL;

HIDDEN MARKOV MODELS; SPEECH SYNTHESIS; SUPPORT VECTOR MACHINES;

SPEECH RECOGNITION;

EID: 84865369980     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2012.2201472     Document Type: Article

References (54)

1. D. A. Reynolds, T. F. Quatieri, and R. B. Dunn, "Speaker verification using adapted Gaussian mixture models," Digital Signal Process., vol. 10, pp. 19-41, 2000. (Pubitemid 30592166)
2. T. Matsui and S. Furui, "Likelihood normalization for speaker verification using a phoneme- and speaker-independent model," Speech Commun., vol. 17, no. 1-2, pp. 109-116, Aug. 1995.
3. Y. W. Lau, M.Wagner, and D. Tran, "Vulnerability of speaker verification to voice mimicking," in Proc. Int. Symp. Intell. Multimedia, Video, Speech Process., Oct. 2004, pp. 145-148. (Pubitemid 40304536)
4. K. Sullivan and J. Pelecanos, "Revisiting carl bildt's impostor:Would a speaker verification system foil him?," in Audio- and Video-Based Biometric Person Authentication, ser. Lecture Notes Computer Science, J. Bigun and F. Smeraldi, Eds. Berlin/Heidelberg, Germany: Springer, 2001, vol. 2091, pp. 144-149. (Pubitemid 33291998)
5. D. Genoud and G. Chollet, "Speech pre-processing against intentional imposture speaker recognition," in Proc. Int. Conf. Spoken Lang. Process. (ICSLP), Dec. 1998, vol. 2, pp. 105-108.
6. B. L. Pellom and J. H. L. Hansen, "An experimental study of speaker verification sensitivity to computer voice-Altered imposters," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 1999, pp. 837-840.
7. J. Lindberg and M. Blomberg, "Vulnerability speaker verification-A study of possible technical imposter techniques.," in Proc. Eur. Conf. Speech Commun. Technol. (Eurospeech), 1999, vol. 3, pp. 1211-1214.
8. D. Matrouf, J.-F. Bonastre, and C. Fredouille, "Effect of speech transformation on impostor acceptance," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), May 2006, vol. 2, pp. 933-936.
9. J.-F. Bonastre, D. Matrouf, and C. Fredouille, "Artificial impostor voice transformation effects on false acceptance rates," in Proc. Int. Speech Commun. Assoc. (Interspeech), Apr. 2007, pp. 2053-2056.
10. J.-F. Bonastre, D. Matrouf, and C. Fredouille, "Transfer function-based voice transformation for speaker recognition," in Proc. IEEE Speaker Lang. Recogn. Workshop (Odyssey), Jun. 2006, pp. 1-6.
11. M. Farrus, D. Erro, and J. Hern, "Speaker recognition robustness to voice conversion," IV J. Reconocimiento Biometrico de Personas, pp. 73-82, Sep. 2008.
12. L.-J. Bo, "Forensic voice identification France," Speech Commun., vol. 31, no. 2-3, pp. 205-224, 2000.
13. T. Masuko, T. Hitotsumatsu, K. Tokuda, and T. Kobayashi, "On the security of HMM-based speaker verification systems against imposture using synthetic speech," in Proc. Eur. Conf. Speech Commun. Technol. (Eurospeech), 1999, pp. 1223-1226.
14. T. Masuko, K. Tokuda, T. Kobayashi, and S. Imai, "Speech synthesis using HMMs with dynamic features," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), May 1996, pp. 389-392.
15. T. Masuko, K. Tokuda, T. Kobayashi, and S. Imai, "Voice characteristics conversion for HMM-based speech synthesis system," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 1997, pp. 1611-1614.
16. T. Masuko, K. Tokuda, and T. Kobayashi, "Imposture using synthetic speech against speaker verification based on spectrum and pitch," in Proc. Int. Conf. Spoken Lang. Process. (ICSLP), 2000, vol. 2, pp. 302-305.
17. F. Bimbot, J. F. Bonastre, C. Fredouille, G. Gravier, I. Magrin-Chagnolleaua, S. Meignier, T.Merlin, J. Ortega-Garcia, and D. A. Reynolds, "A tutorial on text-independent speaker verification," EURASIP J. Appl. Signal Process., vol. 4, pp. 430-451, 2004.
18. T. Kinnunen, E. Karpov, and P. Franti, "Real-Time speaker identification and verification," IEEE Trans. Audio, Speech, Language Process., vol. 14, no. 1, pp. 277-288, Jan. 2006. (Pubitemid 43863473)
19. W. M. Campbell, D. E. Sturim, and D. A. Reynolds, "Support vector machines using GMM supervectors for speaker verification," IEEE Signal Process. Lett., vol. 13, no. 5, pp. 308-311, May 2006.
20. C. Longworth and M. Gales, "Combining derivative and parametric kernels for speaker verification," IEEE Trans. Audio, Speech, Lang. Process., vol. 17, no. 4, pp. 748-757, May 2009.
21. H. Zen, K. Tokuda, and A. W. Black, "Statistical parametric speech synthesis," Speech Commun., vol. 51, no. 11, pp. 1039-1064, Nov. 2009.
22. J.Yamagishi, T. Nose, H. Zen, Z.-H. Ling, T. Toda, K. Tokuda, S. King, and S. Renals, "A robust speaker-Adaptive HMM-based text-To-speech synthesis," IEEE Trans. Speech, Audio, Lang. Process., vol. 17, no. 6, pp. 1208-1230, Aug. 2009.
23. J. Yamagishi, B. Usabaev, S. King, O. Watts, J. Dines, J. Tian, R. Hu, K. Oura, K. Tokuda, R. Karhila, and M. Kurimo, "Thousands of voices for HMM-based speech synthesis-Analysis and application of TTS systems built on various ASR corpora," IEEE Trans. Speech, Audio, Lang. Process., vol. 18, no. 5, pp. 984-1004, Jul. 2010.
24. P. L. De Leon, V. R. Apsingekar, M. Pucher, and J. Yamagishi, "Revisiting the security of speaker verification systems against imposture using synthetic speech," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Mar. 2010, pp. 1798-1801.
25. P. L. De Leon, M. Pucher, and J. Yamagishi, "Evaluation of the vulnerability of speaker verification to synthetic speech," in Proc. IEEE Speaker Lang. Recogn. Workshop (Odyssey), 2010, pp. 151-158.
26. P. L. De Leon, I. Hernaez, I. Saratxaga, M. Pucher, and J. Yamagishi, "Detection of synthetic speech for the problem of imposture," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Dallas, TX, 2011, pp. 4844-4847.
27. T. Satoh, T. Masuko, T. Kobayashi, and K. Tokuda, "A robust speaker verification system against imposture using an HMM-based speech synthesis system," in Proc. Eur. Conf. Speech Commun. Technol. (Eurospeech), 2001, pp. 759-762.
28. J. Pelecanos and S. Sridharan, "Feature warping for robust speaker verification," in Proc. IEEE Speaker Lang. Recogn. Workshop (Odyssey), 2001, pp. 213-218.
29. W. Campbell, D. Sturim, D. Reynolds, and A. Solomonoff, "SVM based speaker verification using GMM supervector kernel and NAP variability compensation," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2006, pp. 97-100.
30. A. Black and N. Cambpbell, "Optimising selection of units from speech database for concatenative synthesis," Proc. Eurospeech-95, pp. 581-584, Sep. 1995.
31. V. Karaiskos, S. King, R. A. J. Clark, and C. Mayo, "The Blizzard challenge 2008," in Proc. Blizzard Challenge, Sep. 2008 [Online]. Available: http://festvox.org/blizzard/bc2008/summary-Blizzard2008.pdf
32. J. Yamagishi, H. Zen, Y.-J. Wu, T. Toda, and K. Tokuda, "The HTS- 2008 system: Yet another evaluation of the speaker-Adaptive HMMbased speech synthesis system the 2008 Blizzard Challenge," in Proc. Blizzard Challenge, Sep. 2008 [Online]. Available: http://festvox.org/blizzard/bc2008/hts- Blizzard2008.pdf
33. H. Kawahara, I. Masuda-Katsuse, and A. Cheveigné, "Restructuring speech representations using a pitch-Adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure sounds," Speech Commun., vol. 27, pp. 187-207, 1999.
34. H. Zen, T. Toda, M. Nakamura, and K. Tokuda, "Details of Nitech HMM-based speech synthesis system for the Blizzard Challenge 2005," IEICE Trans. Inf. Syst., vol. E90-D, no. 1, pp. 325-333, Jan. 2007. (Pubitemid 46145336)
35. H. Zen, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "A hidden semi-Markov model-based speech synthesis system," IEICE Trans. Inf. Syst., vol. E90-D, no. 5, pp. 825-834, May 2007.
36. K. Shinoda and T.Watanabe, "MDL-based context-dependent subword modeling for speech recognition," J. Acoust. Soc. Japan (E), vol. 21, pp. 79-86, Mar. 2000. (Pubitemid 30594111)
37. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-Adaptive training," in Proc. Int. Conf. Spoken Lang. Process. (ICSLP), Oct. 1996, pp. 1137-1140.
38. M. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Comput. Speech Lang., vol. 12, no. 2, pp. 75-98, 1998. (Pubitemid 128383747)
39. J. Yamagishi, T. Kobayashi, Y. Nakano, K. Ogata, and J. Isogai, "Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm," IEEE Trans. Speech, Audio, Lang. Process., vol. 17, no. 1, pp. 66-83, 2009.
40. T. Toda and K. Tokuda, "A speech parameter generation algorithm considering global variance for HMM-based speech synthesis," IEICE Trans. Inf. Syst., vol. E90-D, no. 5, pp. 816-824, May 2007.
41. E. Moulines and F. Charpentier, "Pitch-synchronous waveform processing techniques for text-To-speech synthesis using diphones," Speech Commun., vol. 9, no. 5-6, pp. 453-468, 1990.
42. T. Fukada, K. Tokuda, T. Kobayashi, and S. Imai, "An adaptive algorithm for Mel-cepstral analysis of speech," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Mar. 1992, pp. 137-140.
43. T. F. Quatieri, Discrete-Time Speech Signal Processing Principles and Practice. Upper Saddle River, NJ: Prentice-Hall, 2002.
44. I. Saratxaga, I. Hernaez, D. Erro, E. Navas, and J. Sanchez, "Simple representation of signal phase for harmonic speech models," Electron. Lett., vol. 45, pp. 381-383, 2009.
45. I. Saratxaga, I. Hernaez, I. Odriozola, E. Navas, I. Luengo, and D. Erro, "Using harmonic phase information to improve ASR rate," in Proc. Int. Speech Commun. Assoc. (Interspeech), 2010, pp. 1185-1188.
46. Y. Stylianou, "Harmonic plus noise models for speech, combined with statistical methods, for speech and speaker modification," Ph.D. dissertation, Ecole Nationale Supérieure des Télé communications, Paris, France, 1996.
47. I. Luengo, I. Saratxaga, E. Navas, I. Hernaez, J. Sanchez, and I. Sainz, "Evaluation of pitch detection algorithms under real conditions," in Proc. ICASSP '07, Honolulu, HI, Apr. 2007, pp. 1057-1060.
48. Wall Street Journal Corpus, 2010. [Online]. Available: http://www.ldc. upenn.edu
49. D. B. Paul and J. M. Baker, "The design for the Wall Street Journalbased CSR corpus," in Proc. Workshop Speech Natural Lang., 1992, pp. 357-362.
50. K. P. Li and J. E. Porter, "Normalizations and selection of speech segments for speaker recognition scoring," in Proc. IEEE. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Apr. 1988, vol. 1, pp. 595-598.
51. R. Auckenthaler, M. Carey, and H. Lloyd-Thomas, "Score normalization for test-independent speaker verification system," Digital Signal Process., vol. 10, no. 1, pp. 42-54, 2000. (Pubitemid 30592165)
52. T. Raitio, A. Suni, J. Yamagishi, H. Pulakka, J. Nurminen, M. Vainio, and P. Alku, "HMM-based speech synthesis utilizing glottal inverse filtering," IEEE Trans. Audio, Speech, Lang. Process., vol. 19, no. 1, pp. 153-165, Jan. 2011.
53. S. Imai, K. Sumita, and C. Furuichi, "Mel log spectrum approximation (MLSA) filter for speech synthesis," Electron. Commun. Japan (Part I: Commun.) vol. 66, no. 2, pp. 10-18, 1983 [Online].Available: http://dx. doi.org/10.1002/ecja.4400660203 (Pubitemid 14491503)
54. H. Kawahara, J. Estill, and O. Fujimura, "Aperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system STRAIGHT," in Proc. Models Anal. Vocal Emissions for Biomed. Applicat. (MAVEBA), 2001, pp. 1-6.