8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Synthesis of Vowels and Tones in Thai Language by Articulatory Modeling

Thanate Khaorapapong (1), Montri Karnjanadecha (1), Keerati Inthavisas (2)

(1) Prince of Songkla University, Thailand
(2) Rajamangala Institute of Technology, Thailand

We propose a way of synthesizing Thai vowels, monophthong and diphthong which consist of nine short-long vowel pairs and three short-long vowel pairs respectively. By adjusting the fundamental frequency or pitch contour, the five tonal of these vowels can be synthesized, leading to a total of 120 phonemes. We evaluate the synthesized monophthongs by comparing the first and second formants to standard in terms of different percentages, which result in 9.89% and 7.44% respectively. For the synthesis of diphthongs, we slide from one vocal-tract vowel to another using linear, logarithmic, or exponential functions.

Full Paper

Bibliographic reference.  Khaorapapong, Thanate / Karnjanadecha, Montri / Inthavisas, Keerati (2004): "Synthesis of vowels and tones in Thai language by articulatory modeling", In INTERSPEECH-2004, 1909-1912.