Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis

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

Volumn , Issue , 2014, Pages 3844-3848

  Zen, Heiga ^a   Senior, Andrew ^a  

^a GOOGLE INC   (United States)

Author keywords

deep neural networks; hidden Markov models; mixture density networks; Statistical parametric speech synthesis

Indexed keywords

HIDDEN MARKOV MODELS; MIXTURES; PROBABILITY DENSITY FUNCTION; SIGNAL PROCESSING;

ACOUSTIC FEATURES; DEEP NEURAL NETWORKS; MIXTURE DENSITY; OBJECTIVE AND SUBJECTIVE EVALUATIONS; OBJECTIVE FUNCTIONS; PREDICTION ACCURACY; STATISTICAL PARAMETRIC SPEECH SYNTHESIS; SYNTHESIZED SPEECH;

SPEECH SYNTHESIS;

EID: 84905262874     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2014.6854321     Document Type: Conference Paper

References (35)

1. H. Zen, K. Tokuda, and A. Black, "Statistical parametric speech synthesis," Speech Commn., vol. 51, no. 11, pp. 1039-1064, 2009.
2. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and duration in HMMbased speech synthesis," in Proc. Eurospeech, 1999, pp. 2347-2350.
3. A. Hunt and A. Black, "Unit selection in a concatenative speech synthesis system using a large speech database," in Proc. ICASSP, 1996
4. H. Zen, K. Tokuda, and T. Kitamura, "Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic features," Comput. Speech Lang., vol. 21, no. 1, pp. 153-173, 2007.
5. M. Shannon, H. Zen, and W. Byrne, "Autoregressive models for statistical parametric speech synthesis," IEEE Trans. Acoust. Speech Lang. Process., vol. 21, no. 3, pp. 587-597, 2013.
6. Y.-J. Wu and R.-H. Wang, "Minimum generation error training for HMM-based speech synthesis," in Proc. ICASSP, 2006, pp. 89-92.
7. Y. Qian, Z.-Z.Wu, B.-Y. Gao, and F. Soong, "Improved prosody generation by maximizing joint probability of state and longer units," IEEE Trans. Acoust. Speech Lang. Process., vol. 19, no. 6, pp. 1702-1710, 2011.
8. H. Zen, M. Gales, Y. Nankaku, and K. Tokuda, "Product of experts for statistical parametric speech synthesis," IEEE Trans. Audio Speech Lang. Process., vol. 20, no. 3, pp. 794-805, 2012.
9. T. Koriyama, T. Nose, and T. Kobayashi, "Statistical parametric speech synthesis based on Gaussian process regression," IEEE Journal of Selected Topics in Signal Process., 2013.
10. S.-Y. Kang, X.-J. Qian, and H. Meng, "Multi-distribution deep belief network for speech synthesis," in Proc. ICASSP, 2013, pp. 8012-8016.
11. Z.-H. Ling, L. Deng, and D. Yu, "Modeling spectral envelopes using restricted Boltzmann machines and deep belief networks for statistical parametric speech synthesis," IEEE Trans. Acoust. Speech Lang. Process., vol. 21, no. 10, pp. 2129-2139, 2013.
12. G. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kingsbury, "Deep neural networks for acoustic modeling in speech recognition," IEEE Signal Process. Magazine, vol. 29, no. 6, pp. 82-97, 2012.
13. H. Zen, A. Senior, and M. Schuster, "Statistical parametric speech synthesis using deep neural networks," in Proc. ICASSP, 2013, pp. 7962-7966.
14. R. Fernandez, A. Rendel, B. Ramabhadran, and R. Hoory, "f0 contour prediction with a deep belief network-Gaussian process hybrid model," in Proc. ICASSP, 2013, pp. 6885-6889.
15. H. Lu, S. King, and O. Watts, "Combining a vector space representation of linguistic context with a deep neural network for text-to-speech synthesis," in Proc. ISCA SSW8, 2013, pp. 281-285.
16. K. Tokuda, H. Zen, and A. Black, "An HMM-based speech synthesis system applied to English," in Proc. IEEE Speech Synthesis Workshop, 2002, CD-ROM Proceeding.
17. H. Zen, "Deep learning in speech synthesis," in Keynote speech given at ISCA SSW8, 2013, http://research.google.com/pubs/ archive/41539.pdf.
18. C. Bishop, "Mixture density networks," Tech. Rep. NCRG/94/004, Neural Computing Research Group, Aston University, 1994.
19. M. Schuster, On supervised learning from sequential data with applications for speech recognition, Ph.D. thesis, Nara Institute of Science and Technology, 1999.
20. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, "Speech parameter generation algorithms for HMM-based speech synthesis," in Proc. ICASSP, 2000, pp. 1315-1318.
21. K. Oura, H. Zen, Y. Nankaku, A. Lee, and K. Tokuda, "Tying covariance matrices to reduce the footprint of HMM-based speech synthesis systems," in Proc. Interspeech, 2009, pp. 1759-1762.
22. 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, 2007.
23. K. Richmond, "Trajectory mixture density networks with multiple mixtures for acoustic-articulatory inversion," in Advances in Nonlinear Speech Processing, pp. 263-272. Springer, 2007.
24. B. Uria, I. Murray, S. Renals, and K. Richmond, "Deep architectures for articulatory inversion," in Proc. Interspeech, 2012, pp. 867-870.
25. H. Zen, T. Toda, M. Nakamura, and T. Tokuda, "Details of the Nitech HMM-based speech synthesis system for the Blizzard Challenge 2005," IEICE Trans. Inf. Syst., vol. E90-D, no. 1, pp. 325-333, 2007.
26. T. Fukada, K. Tokuda, T. Kobayashi, and S. Imai, "An adaptive algorithm for mel-cepstral analysis of speech," in Proc. ICASSP, 1992, pp. 137-140.
27. 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, 2007.
28. K. Tokuda, T. Masuko, N. Miyazaki, and T. Kobayashi, "Multi-space probability distribution HMM," IEICE Trans. Inf. Syst., vol. E85-D, no. 3, pp. 455-464, 2002.
29. K. Shinoda and T. Watanabe, "Acoustic modeling based on the MDL criterion for speech recognition," in Proc. Eurospeech, 1997, pp. 99-102.
30. K. Yu and S. Young, "Continuous F0 modelling for HMM based statistical parametric speech synthesis," IEEE Trans. Audio Speech Lang. Process., vol. 19, no. 5, pp. 1071-1079, 2011.
31. A. Senior, G. Heigold, M. Ranzato, and K. Yang, "An empirical study of learning rates in deep neural networks for speech recognition," in Proc. ICASSP, 2013, pp. 6724-6728.
32. J. Duchi, E. Hazan, and Y. Singer, "Adaptive subgradient methods for online learning and stochastic optimization," The Journal of Machine Learning Research, pp. 2121-2159, 2011.
33. M. Zeiler, M. Ranzato, R. Monga, M. Mao, K. Yang, Q.-V. Le, P. Nguyen, A. Senior, V. Vanhoucke, J. Dean, and G. Hinton, "On rectified linear units for speech processing," in Proc. ICASSP, 2013, pp. 3517-3521.
34. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Incorporation of mixed excitation model and postfilter into HMMbased text-to-speech synthesis," IEICE Trans. Inf. Syst., vol. J87-D-II, no. 8, pp. 1563-1571, 2004.
35. T. Toda, A. Black, and K. Tokuda, "Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory," IEEE Trans. Audio Speech Lang. Process., vol. 15, no. 8, pp. 2222-2235, 2007.