F0 contour prediction with a deep belief network-Gaussian process hybrid model

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

Volumn , Issue , 2013, Pages 6885-6889

  Fernandez, Raul ^a   Rendel, Asaf ^b   Ramabhadran, Bhuvana ^a   Hoory, Ron ^b  

^a IBM T J WATSON RESEARCH CENTER   (United States)

^b IBM HAIFA RESEARCH LAB   (Israel)

Author keywords

Gaussian processes; intonation generation; neural networks; speech synthesis

Indexed keywords

DEEP BELIEF NETWORKS; GAUSSIAN PROCESS REGRESSION; GAUSSIAN PROCESSES; HIGH-LEVEL STRUCTURE; INTONATION GENERATIONS; NONLINEAR FEATURES; PARAMETRIC SYNTHESIS; SPEECH SYNTHESIS SYSTEM;

BAYESIAN NETWORKS; FORECASTING; GAUSSIAN DISTRIBUTION; NEURAL NETWORKS; REGRESSION ANALYSIS; SIGNAL PROCESSING; SPEECH SYNTHESIS;

GAUSSIAN NOISE (ELECTRONIC);

EID: 84890522099     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6638996     Document Type: Conference Paper

References (14)

1. G. Hinton, S. Osindero, and Y. Teh, "A fast learning algorithm for Deep Belief Nets," Neural Computation, vol. 18, pp. 1527-1554, 2006
2. T. N. Sainath, B. Kingsbury, B. Ramabhadran, P. Fousek, P. Novak, and A. Mohamed, "Making Deep Belief Networks effective for large vocabulary continuous speech recognition," in Proc. ASRU, Hawaii, 2011
3. G. Hinton, "A practical guide to training Restricted Boltzmann Machines," University of Toronto, Tech. Rep. 2010-003, 1996
4. C. Rasmussen and C. Williams, Gaussian Processes for Machine Learning. MIT Press, 2006
5. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, "Speech parameter generation algorithms for HMMbased speech synthesis," in ICASSP, 2000, pp. 1315-1318
6. J. Quinonero-Candela and C. Rasmussen, "A unifying view of sparse approximate Gaussian process regression," Journal of Machine Learning Research, vol. 6, pp. 1939-1959, 2005
7. A. Sakurai, K. Hirose, and N. Minematsu, "Generation of F0 contours using a model-constrained data-driven method," in ICASSP, 2001, pp. 817-820
8. S. Vishnubhotlan, R. Fernandez, and B. Ramabhadran, "An autoencoder neural-network based low-dimensionality approach to excitation modeling for HMM-based text-to-speech," ICASSP, vol. 2, pp. 4614-4617, March 2010
9. N. Pilkington, H. Zen, and M. Gales, "Gaussian process experts for voice conversion," in Interspeech, 2011, pp. 2761-2764
10. H. Park and C. Yoo, "Gaussian process dynamical models for phoneme classification," in NIPS 2011: Workshop on Bayesian Nonparametrics, 2011
11. G. Henter, M. Frean, and W. Kleijn, "Gaussian process dynamical models for nonparametric speech representation and synthesis," in ICASSP, 2012, pp. 4505-4508
12. S. J. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book Version 3.4. Cambridge University Press, 2006
13. Y. Yamagishi, H. Zen, T. Toda, and K. Tokuda, "Speakerindependent HMM-based speech synthesis system-HTS-2007 system for the Blizzard Challenge," in Blizzard 2007, 2007
14. "HMM-based Speech Synthesis System (HTS)," http://hts.sp. nitech.ac.jp/.