Abstract
The objective of this work is to develop an articulatory model which comprises the velum so as to be able to synthesize nasal vowels and consonants in French. Unlike one exception of a velum model developed from static 3D MRI images there is no model derived from articulatory data that can be used within a vocal tract articulatory model. Our model is derived from X-ray films of the DOCVACIM database. The velum contour has been tracked semi-automatically and then carefully checked and corrected from 1050 mid-sagittal images of the vocal tract. Principal component analysis has been applied onto these contours. The first component represents more than 50% of the variance and controls the velum opening. The next two components capture 20 and 12 % of the variance, respectively, and explain the deformation of the velum between open and close configurations. In parallel a series of MRI images of nasal vowels and consonant of French was analyzed. The velum opening roughly has a shape of a bean, whose length is almost constant for one speaker and width is given by the 2D articulatory model. Together with an evaluation of the nasal cavities this model can be used for articulatory synthesis.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.