A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis

@article{Toda2005ASP,
  title={A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis},
  author={T. Toda and K. Tokuda},
  journal={IEICE Trans. Inf. Syst.},
  year={2005},
  volume={90-D},
  pages={816-824}
}
This paper describes a novel parameter generation algorithm for an HMM-based speech synthesis technique. The conventional algorithm generates a parameter trajectory of static features that maximizes the likelihood of a given HMM for the parameter sequence consisting of the static and dynamic features under an explicit constraint between those two features. The generated trajectory is often excessively smoothed due to the statistical processing. Using the over-smoothed speech parameters usually… Expand
474 Citations
Modulation spectrum-constrained trajectory training algorithm for HMM-based speech synthesis
  • 1
  • PDF
A speech parameter generation algorithm using local variance for HMM-based speech synthesis
  • 2
  • Highly Influenced
  • PDF
Trajectory training considering global variance for HMM-based speech synthesis
  • T. Toda, S. Young
  • Computer Science
  • 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2009
  • 30
  • PDF
A Parameter Generation Algorithm Using Local Variance for HMM-Based Speech Synthesis
  • 17
Global variance modeling on frequency domain delta LSP for HMM-based speech synthesis
  • 10
  • PDF
Minimum Kullback–Leibler Divergence Parameter Generation for HMM-Based Speech Synthesis
  • Zhenhua Ling, Lirong Dai
  • Mathematics, Computer Science
  • IEEE Transactions on Audio, Speech, and Language Processing
  • 2012
  • 23
  • PDF
Analysis of spectral enhancement using global variance in HMM-based speech synthesis
  • 12
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 32 REFERENCES
Speech parameter generation algorithms for HMM-based speech synthesis
  • 1,081
  • PDF
Speech parameter generation from HMM using dynamic features
  • 303
Spectral conversion based on maximum likelihood estimation considering global variance of converted parameter
  • T. Toda, A. Black, K. Tokuda
  • Mathematics, Computer Science
  • Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.
  • 2005
  • 135
  • PDF
Hidden Markov models based on multi-space probability distribution for pitch pattern modeling
  • 311
Unit selection in a concatenative speech synthesis system using a large speech database
  • Andrew J. Hunt, A. Black
  • Computer Science
  • 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings
  • 1996
  • 1,314
  • PDF
Applying the harmonic plus noise model in concatenative speech synthesis
  • Y. Stylianou
  • Computer Science
  • IEEE Trans. Speech Audio Process.
  • 2001
  • 353
  • PDF
An HMM-based speech synthesis system applied to English
  • 318
  • PDF
...
1
2
3
4
...