Training algorithm to deceive Anti-Spoofing Verification for DNN-based speech synthesis

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2017, Pages 4900-4904

  Saito, Yuki ^a   Takamichi, Shinnosuke ^a   Saruwatari, Hiroshi ^a  

^a UNIVERSITY OF TOKYO   (Japan)

Author keywords

anti spoofing verification; DNN based speech synthesis; generative adversarial training; multitask learning; training algorithm

Indexed keywords

EID: 85023772724     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2017.7953088     Document Type: Conference Paper

References (31)

1. H. Zen, K. Tokuda, and A. Black, "Statistical parametric speech synthesis," Speech Communication, Vol. 51, no. 11, pp. 1039-1064, 2009.
2. K. Tokuda, Y Nankaku, T. Toda, H. Zen, J. Yamagishi, and K. Oura, "Speech synthesis based on hidden Markov models," Proceedings of the IEEE, Vol. 101, no. 5, pp. 1234-1252, 2013.
3. Z. H. Ling, S. Y Kang, H. Zen, A. Senior, M. Schuster, X. J. Qian, H. Meng, and L. Deng, "Deep learning for acoustic modeling in parametric speech generation: A systematic review of existing techniques and future trends," IEEE Signal Processing Magazine, Vol. 32, no. 3, pp. 35-52, 2015.
4. Y J. Wu and R. H. Wang, "Minimum generation error training for HMM-based speech synthesis," in Proc. ICASSP, Toulouse, France, May 2006, pp. 89-92.
5. Z. Wu and S. King, "Improving trajectory modeling for DNN-based speech synthesis by using stacked bottleneck features and minimum trajectory error training," IEEE Transactions on Audio, Speech, and Language Processing, Vol. 24, no. 7, pp. 1255-1265, 2016.
6. T. Toda, L. H. Chen, D. Saito, F. Villavicencio, M. Wester, Z. Wu, and J. Yamagishi, "The Voice Conversion Challenge 2016," in Proc. INTERSPEECH, California, U.S.A., Sep. 2016, pp. 1632-1636.
7. Y. Ijima, T. Asami, and H. Mizuno, "Objective evaluation using association between dimensions within spectral features for statistical parametric speech synthesis," in Proc. INTERSPEECH, California, U.S.A., Sep. 2016, pp. 337-341.
8. T. Toda, A. W. Black, and K. Tokuda, "Voice conversion based on maximum likelihood estimation of spectral parameter trajectory," IEEE Transactions on Audio, Speech, and Language Processing, Vol. 15, no. 8, pp. 2222-2235, 2007.
9. Y. Ohtani, M. Tamura, M. Morita, T. Kagoshima, and M. Akamine, "Histogram-based spectral equalization for HMM-based speech synthesis using mel-LSP," in Proc. INTERSPEECH, Portland, U.S.A., Sep. 2012.
10. S. Takamichi, T. Toda, A. W. Black, G. Neubig, S. Sakti, and S. Nakamura, "Postfilters to modify the modulation spectrum for statistical parametric speech synthesis," IEEE Transactions on Audio, Speech, and Language Processing, Vol. 24, no. 4, pp. 755-767, 2016.
11. S. Takamichi, T. Toda, A. W. Black, and S. Nakamura, "Modulation spectrum-constrained trajectory training algorithm for GMM-based voice conversion," in Proc. ICASSP, Brisbane, Australia, Apr. 2015, pp. 4859-4863.
12. K. Hashimoto, K. Oura, Y Nankaku, and K. Tokuda, "Trajectory training considering global variance for speech synthesis based on neural networks," in Proc. ICASSP, Shanghai, China, Mar. 2016, pp. 5600-5604.
13. T. Nose and A. Ito, "Analysis of spectral enhancement using global variance in HMM-based speech synthesis," in Proc. INTERSPEECH, MAX Atria, Singapore, May 2014, pp. 2917-2921.
14. H. Zen, A. Senior, and M. Schuster, "Statistical parametric speech synthesis using deep neural networks," in Proc. ICASSP, Vancouver, Canada, May 2013, pp. 7962-7966.
15. Z. Wu, P. L. D. Leon, C. Demiroglu, A. Khodabakhsh, S. King, Z. Ling, D. Saito, B. Stewart, T. Toda, M. Wester, and J. Yamagishi, "Anti-spoofing for text-independent speaker verification: An initial database, comparison of countermeasures, and human performance," IEEE Transactions on Audio, Speech, and Language Processing, Vol. 24, no. 4, pp. 768-783, 2016.
16. N. Chen, Y Qian, H. Dinkel, B. Chen, and K. Yu, "Robust deep feature for spoofing detection - the SJTU system for ASVspoof 2015 Challenge," in Proc. INTERSPEECH, Dresden, Germany, Sep. 2015, pp. 2097-2101.
17. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y Bengio, "Generative adversarial nets," in Advances in Neural Information Processing Systems 27, pp. 2672-2680. 2014.
18. G. E. Hinton and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, Vol. 313, no. 5786, pp. 504-507, 2006.
19. H. Zen and H. Sak, "Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis," in Proc. ICASSP, Brisbane, Australia, Apr. 2015, pp. 4470-4474.
20. B. Huang, D. Ke, H. Zheng, B. Xu, Y Xu, and K. Su, "Multitask learning deep neural networks for speech feature denoising," in Proc. INTERSPEECH, Dresden, Germany, Sep. 2015, pp. 2464-2468.
21. S. Reed, Z. Akata, X. Yan, L. Logeswaran, B. Schiele, and H. Lee, "Generative adversarial text-to-image synthesis," in Proc. ICML, 2016, pp. 1060-1069.
22. T. R. Marco, S. Sameer, and G. Carlos, ""Why should I trust you?": Explaining the predictions of any classifier," in Proc. KDD, San Francisco, U.S.A., Aug. 2016, pp. 1135-1164.
23. D. N. Reshef, Y A. Reshef, H. K. Finucane, S. R. Grossman, G. McVean, P. J. Turnbaugh, E. S. Lander, M. Mitzenmacher, and P. C. Sabeti, "Detecting novel associations in large data sets," vol. 334, no. 6062, pp. 1518-1524, 2011.
24. M. Abe, Y Sagisaka, T. Umeda, and H. Kuwabara, "ATR technical repoart,", no. TR-I-0166M, 1990.
25. H. Kawahara, Jo 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 MAVEBA 2001, Firentze, Italy, Sep. 2001, pp. 1-6.
26. Y. Ohtani, T. Toda, H. Saruwatari, and K. Shikano, "Maximum likelihood voice conversion based on GMM with STRAIGHT mixed excitation," in Proc. INTERSPEECH, Pittsburgh, U.S.A., Sep. 2006, pp. 2266-2269.
27. H. Kawahara, I. Masuda-Katsuse, and A. D. Cheveigne, "Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds," Speech Communication, Vol. 27, no. 3-4, pp. 187-207, 1999.
28. S. Takamichi, K. Kobayashi, K. Tanaka, T. Toda, and S. Nakamura, "The NAIST text-to-speech system for the Blizzard Challenge 2015," in Proc. Blizzard Challenge workshop, Berlin, Germany, Sep. 2015.
29. X. Glorot, A. Bordes, and Y Bengio, "Deep sparse rectifier neural networks," in Proc. AISTATS, Lauderdale, U.S.A., Apr. 2011, pp. 315-323.
30. J. Duchi, E. Hazan, and Y Singer, "Adaptive subgradient methods for online learning and stochastic optimization," Journal of Machine Learning Research, Vol. 12, pp. 2121-2159, 2011.
31. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, Vol. 9, no. 8, pp. 1735-1780, 1997.