Establishment of Indonesian viseme sequences using hidden Markov model based on affection

Abstract

Every language has different characteristics, one of which is how to pronounce the language. Pronunciation accompanied by emotional expression are increasingly making different characteristics. This research proposes the establishment of natural Indonesian viseme order influenced by the expression of emotion. This system converts the text input of an Indonesian sentence into a sequence Indonesian viseme to be influenced by the affection. Animation of mouth shape and lip movements are made to complement the visualization of natural speech, which is resulted from the establishment Indonesian viseme model. The method used in the natural Indonesian viseme sequence, is using statistical approach through Viterbi algorithm Hidden Markov Model.