Text-to-Speech Synthesis System for Mongolian Language
Taun Duc Pham
MetadataShow full item record
Speech synthesis (text-to-speech) is the process of converting written text into machine generated synthetic speech. At this time, concatenative synthesis (unit selection) is judged the highest quality synthesis technique. Cancatenative synthesis techniques not only provide the most natural sounding speech synthesis, they are also the most accessible to the general user. Concatenative speech synthesis systems render speech by concatenating pre-recorded speech units. This thesis is the first to design and develop an intelligible and natural sounding corpus-based concatenative speech synthesis system for Mongolians.
Thesis (PhD Doctorate)
Doctor of Philosophy (PhD)
Griffith School of Engineering
Item Access Status
Restricted (Permanent or embargo)
Exemption from digital deposit of this thesis has been granted.
Speech synthesis text-to-speech
Concatenative speech synthesis