Glottal source modeling for singing voice synthesis
Back to research page
Aug 24, 2000
Abstract
Naturalness
of sound quality is essential for singing-voice synthesis. Since 95% of singing
is voiced sound (Cook, 1990), the focus of this paper is to improve the
naturalness of the vowel tone quality via glottal excitation modeling. We
propose to use the LF-model (Fant et al., 1985) for the glottal wave shape in
conjunction with pitch-synchronous, amplitude-modulated Gaussian noise, which
adds an aspiration component to the glottal excitation. The associated analysis
and synthesis procedures are also provided in this paper. By analyzing baritone
recordings, we have found simple rules to change voice qualities from
“laryngealized” (or “pressed”), to normal, to “breathy” phonation.
You can download my ICMC2000 paper for details.
Sound Examples
You can control the vocal texture
by a single parameter! I have implemented a simple demo application. Its
interface looks like this:
Here are some sound examples generated
from this application.
·
Vowel /a/, Low Pitch, Press phonation (VTC =
0.1)
·
Vowel /a/, Low Pitch, Normal phonation (VTC =
0.5)
·
Vowel /a/, Low Pitch, Breathy phonation (VTC =
1)
email: Hui-Ling Lu