Text to Speech plays a alive role in giving information to the general community who have trouble reading document but can understand spoken language. In Bhutan, aforementioned system were not handy and building a order will leverage the use of the language by various segment of family. This article defines an attempt to create a functioning model of a Text to Speech system for the Dzongkha speech by creating a copy or grapheme table for phonetic transcription from Dzongkha idea to its comparable telephone set. The transcription tables for sound unit of speech and vowels have been produced as though they allow for upgraded computer unity. 3000 phrases were painstakingly transcribed and written using a alone male voice. On the FESTIVAL platform, the voice combining was based on a statistical approach accompanying concatenative speech concoction. The model is generated utilizing the two variants CLUSTERGEN and CLUNITS of the FESTIVAL talk tools FESTVOX place the earlier design produce more natural speech than the later for the big data set. The growth of system example is of the first kind for the Dzongkha language in spite of attempts should by researchers.
Author(s) Details:
Yeshi Wangchuk,
Information
Technology Department, College of Science and Technology, Royal University of
Bhutan, Rinchending, Phuentsholing, 21002, Bhutan.
Kamal
K. Chapagai,
Electronics
and Communication Engineering Department, College of Science and Technology,
Royal University of Bhutan, Rinchending, Phuentsholing, 21002, Bhutan.
Pema Galey,
Information Technology Department, College of Science and
Technology, Royal University of Bhutan, Rinchending, Phuentsholing, 21002,
Bhutan.
Yeshi Jamtsho,
Information Technology Department, College of Science and
Technology, Royal University of Bhutan, Rinchending, Phuentsholing, 21002,
Bhutan.
Please see the link here: https://stm.bookpi.org/RATMCS-V4/article/view/11816
