This paper describes the Isarn speech synthesis system, which is a regional dialect spoken in the Northeast of Thailand. In this study, we focus to improve
the prosody generation of the system by using the additional context features. In order to develop the system, the speech parameters (Mel-ceptrum and
fundamental frequencies of phoneme within different phonetic contexts) were modelled using Hidden Markov Models (HMM). Synthetic speech was generated
by converting the input text into contextdependent phonemes. Speech parameters were generated from the trained HMM, according to the context-dependent phonemes, and were then synthesized through a speech vocoder.Etc...
Keywords
Text-to-speech, speech synthesis, HMM, Isarn
ECTI TRANSACTIONS ON COMPUTER INFORMATION TECHNOLOGY