Abstract
This paper is concerned with speech training systems which intend to show how to articulate vowels and some consonants displaying vocal tract shapes. The first one is implemented on a microcomputer and relates to articulation of vowels. It shows whether the uttered vowel is more similar to the intended vowel than to each of the other vowels, and instructs how to articulate the vowel by displaying both the reference lateral vocal tract shape and the one presumed from the uttered voice. It can adapt its performance automatically to the child's progress pace in learning. It can be used as a discriminator of words, and is also suitable for self-teaching. The other system estimates the vocal tract shapes of vowels and of some stop and fricative consonants from uttered speech waves, and instructs how to articulate. For the articulation of vowels, the system points out defects about the place of articulation and opening of lips, and for the articulation of consonants, it points out the defect about the place of articulation and displays how to correct the articulation.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call