An autoencoder neural-network based low-dimensionality approach to excitation modeling for HMM-based text-to-speech

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

Volumn , Issue , 2010, Pages 4614-4617

  Vishnubhotla, Srikanth ^a   Fernandez, Raul ^b   Ramabhadran, Bhuvana ^b  

^a UNIVERSITY OF MARYLAND   (United States)

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

Author keywords

Autoencoders; Excitation modeling; Hidden Markov models; Neural networks; Speech synthesis

Indexed keywords

DIGITAL STORAGE; HIDDEN MARKOV MODELS; LEARNING SYSTEMS; NEURAL NETWORKS;

AUTO ENCODERS; DATA DRIVEN; EXCITATION MODELING; HIDDEN-MARKOV MODELS; HMM-BASED; HMM-TTS; LOW DIMENSIONALITY; NETWORK-BASED; NEURAL-NETWORKS; TEXT TO SPEECH;

SPEECH SYNTHESIS;

EID: 78049412607     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495546     Document Type: Conference Paper

References (10)

1. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis," in Eurospeech, 1999, pp. 1223-1226.
2. R. Maia, T. Toda, H. Zen, Y. Nankaku, and K. Tokuda, "A trainable excitation model for HMM-based speech synthesis," in Interspeech, 2007, pp. 1909-1912.
3. K. Tokuda and H. Zen, "Fundamentals and recent advances in HMM-based speech synthesis," in Interspeech, 2009.
4. R. Maia, T. Toda, K. Tokuda, S. Sakai, and S. Nakamura, "On the state definition for a trainable excitation model in HMM-based speech synthesis," in ICASSP, 2008, pp. 3965-3968.
5. J. P. Cabral, S. Renals, K. Richmond, and J. Yamagishi, "Towards an improved modeling of the glottal source in statistical parametric speech synthesis," in Proc. Sixth ISCA Workshop on Speech Synth., 2007, pp. 131-136.
6. T. Drugman, A. Moinet, T. Dutoit, and G. Wilfart, "Using a pitch-synchronous residual codebook for hybrid HMM/frame selection speech synthesis," in ICASSP, 2009, pp. 3793-3796.
7. M. Sakamoto and T. Saito, "An automatic pitch marking method using wavelet transform," in ICSLP, 2000, vol. 3, pp. 650-653.
8. G. E. Hinton and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, vol. 313, no. 5786, pp. 504-507, July 2006.
9. M. Á. Carreira-Perpiñán and G.E. Hinton, "On contrastive divergence learning," in Artificial Intelligence and Statistics, 2005, pp. 33-41.
10. "Speech Signal Processing Toolkit (SPTK)," Version 3.2, http://sp-tk.sourceforge.net/.