Objective distance measures for assessing concatenative speech synthesis

@inproceedings{Chen1999ObjectiveDM,
  title={Objective distance measures for assessing concatenative speech synthesis},
  author={Jing-Dong Chen and Nick Campbell},
  booktitle={EUROSPEECH},
  year={1999}
}
Several di erent acoustic transforms of the speech signal are compared for use in the assessment and evaluation of concatenative speech synthesis. The transforms tested include LPC, LSP, MFCC, bispectrum, Mellin transform of the log spectrum, WignerVille distribution (WVD), etc. The computed distances between a synthesised utterance and a naturally spoken version of the same sentence are compared by correlation with perceptually-based scores obtained from a MOS evaluation. The results show that… CONTINUE READING
Highly Cited
This paper has 17 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
Showing 1-10 of 10 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 14 references

Speech Synthesis Evaluation by Objective Distance Measures", in SP- 99-xxx

J. D. Chen, W. N. Campbell
Tech Rept of the IEICE, • 1999
View 1 Excerpt

Improved Speech Feature Based on the Modi ed Mellin Transform for Speech Recognition

J. Chen, Bo Xu, Taiyi Huan, An
Proc ICCSLP98, • 1998
View 1 Excerpt

Large Vocabulary Speech Recognition: A Review

Steve Young
IEEE Sig Proc Magazine, • 1996
View 1 Excerpt

Timefrequency Representation Based Cepstral Processing for Speech Recognition

Adam, B. Fineberg, Kevin C. Yu
In Proc ICASSP96, • 1996
View 2 Excerpts

A localization property of line spectrum frequencies

IEEE Trans. Speech and Audio Processing • 1994
View 1 Excerpt

Speech Science and Technology

Shuzo Saito
IOS PRESS, • 1992
View 1 Excerpt

Optimization of perceptually-based ASR front-end", in the proceeding of ICASSP88

Hynek Hermansky, Jean Claude Junqua
Vol. I, • 1988
View 1 Excerpt

Similar Papers

Loading similar papers…