A frequency-weighted post-filtering transform for compensation of the over-smoothing effect in HMM-based speech synthesis

@article{Eyben2014AFP,
  title={A frequency-weighted post-filtering transform for compensation of the over-smoothing effect in HMM-based speech synthesis},
  author={Florian Eyben and Yannis Agiomyrgiannakis},
  journal={2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2014},
  pages={275-279}
}
Over-smoothing is one of the major sources of quality degradation in statistical parametric speech synthesis. Many methods have been proposed to compensate over-smoothing with the speech parameter generation algorithm considering Global Variance (GV) being one of the most successfull. This paper models over-smoothing as a radial relocation of poles and zeros of the spectral envelope towards the origin of the z-plane and uses radial scaling to enhance spectral peaks and to deepen spectral valeys… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-4 of 4 extracted citations

Two-Band Radial Postfiltering in Cepstral Domain with Application to Speech Synthesis

IEEE Signal Processing Letters • 2016
View 3 Excerpts
Highly Influenced

Postfilters to Modify the Modulation Spectrum for Statistical Parametric Speech Synthesis

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2016
View 1 Excerpt

Modulation spectrum-based post-filter for GMM-based Voice Conversion

Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific • 2014
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 19 references

Discrete-time speech signal processing: principles and practice

T. F. Quatieri
Pearson education, • 2008
View 3 Excerpts
Highly Influenced

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

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 1 Excerpt

Fast, low-artifact speech synthesis considering global variance

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 1 Excerpt

Modeling spectral envelopes using restricted Boltzmann machines for statistical parametric speech synthesis

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013

Statistical parametric speech synthesis using deep neural networks

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 2 Excerpts

Global variance modeling on frequency domain delta LSP for HMM-based speech synthesis

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2011
View 1 Excerpt

Voice quality variation with fundamental frequency in english and mandarin

P. Keating, Y.-L. Shue
The Journal of the Acoustical Society of America, vol. 126, no. 4, pp. 2221–2221, 2009. • 2009
View 1 Excerpt

Similar Papers

Loading similar papers…