Ausdang Thangthai

Learn More
This paper presents applications of five famous learning methods for Thai phrase break prediction. Phrase break prediction is particularly important for our Thai text-to-speech synthesizer (TTS), where input Thai text has no word and sentence boundary. The learning methods include a POS sequence model, CART, RIPPER, SLIPPER and neural network. Features(More)
This paper presents naturalness improvement in Thai unit-selection text-to-speech synthesis (TTS) based on prosody modeling. Although several modeling approaches of prosodic parameters in Thai speech have been proposed, they have not been proven to provide a promising performance when practically assembling in a synthesizer. In this paper, two learning(More)