Speech parametric representation for hmm based speech synthesis
Joint Authors
Darwish, M. G.
Abd al-Hamid, O.
Afifi, M.
Source
International Journal of Intelligent Computing and Information Sciences
Issue
Vol. 7, Issue 2 (31 Jul. 2007)11 p.
Publisher
Ain Shams University Faculty of Computer and Information Sciences
Publication Date
2007-07-31
Country of Publication
Egypt
No. of Pages
11
Main Subjects
Information Technology and Computer Science
Abstract EN
MM based speech synthesis, where speech parameters are generated directly from HMM models, is a relatively new speech synthesis technique.
In this paper, we propose a parametric representation for the HMM based speech synthesis.
In this representation, a multi-band excitation model is used, and a number of samples extracted from the spectral envelop are used as spectral parameters.
In synthesis, voiced and unvoiced speech parts are mixed according to bands voicing parameters.
The voiced part is generated based on a harmonic sinusoidal model, and unvoiced part is generated as white noise filtered using short time fourier transform.
Experimental results show that the proposed parametric representation improved the quality.
American Psychological Association (APA)
Abd al-Hamid, O.& Darwish, M. G.& Afifi, M.. 2007. Speech parametric representation for hmm based speech synthesis. International Journal of Intelligent Computing and Information Sciences،Vol. 7, no. 2.
https://search.emarefa.net/detail/BIM-284948
Modern Language Association (MLA)
Abd al-Hamid, O.…[et al.]. Speech parametric representation for hmm based speech synthesis. International Journal of Intelligent Computing and Information Sciences Vol. 7, no. 2 (Jul. 2007).
https://search.emarefa.net/detail/BIM-284948
American Medical Association (AMA)
Abd al-Hamid, O.& Darwish, M. G.& Afifi, M.. Speech parametric representation for hmm based speech synthesis. International Journal of Intelligent Computing and Information Sciences. 2007. Vol. 7, no. 2.
https://search.emarefa.net/detail/BIM-284948
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references.
Record ID
BIM-284948