EUVIMEDEUVIMED entdecken
Crossref

A Measure of Smoothness in Synthesized Speech

Phung Trung Nghia, Nguyen Van Tao, Pham Thi Mai Huong, Nguyen Thi Bich Diep, Phung Thi Thu Hien

REV Journal on Electronics and Communications · 2016

DOI: 10.21553/rev-jec.106 ↗

Kurz gefasst

Fachartikel in der Zeitschrift REV Journal on Electronics and Communications, 2016. Verfasst von Phung Trung Nghia und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The articulators typically move smoothly during speech production. Therefore, speech features of natural speech are generally smooth. However, over-smooth causes the “muffleness" and the reduction in identification emotions / expressions / styles in synthesized speech that can affect to the perception of the naturalness in synthesized speech. In the literature, statistical variances of static spectral features have been used as a measure of smoothness in synthesized speech but they are not sufficient enough. This paper aims to propose a speech smoothness measure that can be efficiently applied to evaluate the smoothness of synthesized speech. Experiments show that the proposed measures are reliable and efficient to measure smoothness of different kinds of synthesized speech.

Zitieren

APA

Nghia, P. T., Tao, N. V., Huong, P. T. M., Diep, N. T. B., & Hien, P. T. T. (2016). A Measure of Smoothness in Synthesized Speech. REV Journal on Electronics and Communications. https://doi.org/10.21553/rev-jec.106

Vancouver

Nghia PT, Tao NV, Huong PTM, Diep NTB, Hien PTT. A Measure of Smoothness in Synthesized Speech. REV Journal on Electronics and Communications. 2016. doi:10.21553/rev-jec.106

BibTeX
@article{Nghia2016,
  author = {Nghia, Phung Trung and Tao, Nguyen Van and Huong, Pham Thi Mai and Diep, Nguyen Thi Bich and Hien, Phung Thi Thu},
  title = {A Measure of Smoothness in Synthesized Speech},
  journal = {REV Journal on Electronics and Communications},
  year = {2016},
  doi = {10.21553/rev-jec.106}
}
Kostenlos starten →